handsonai · Nerlo

AI review of these findings

Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.

Upheld as real: 245
Dismissed as false positives: 470
Not reviewed: 4

Out of 719 findings across every scanner that examined this package. 1 of 3 findings rated critical by their scanner was among the dismissals.

Not reviewed is not the same as clean. Those 4 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

Why those were dismissed

Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.

284 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: FILE_MAGIC_MISMATCH, MANIFEST_MISSING_LICENSE · Files: /repo/registry-template/tools/fixtures/valid-bundle/registry/workflows/third-workflow.md, /repo/registry-template/tools/fixtures/broken/multiline-frontmatter/registry/workflows/first-workflow.md, /repo/registry-template/tools/fixtures/broken/double-claim/registry/workflows/second-workflow.md and 272 more · reported by cisco-skill-scanner
179 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, FILE_MAGIC_MISMATCH, SOCIAL_ENG_ANTHROPIC_IMPERSONATION and 4 more · Files: src/content/docs/llms-full.txt, src/content/docs/ai-workflow-framework/deconstruct.md, src/content/docs/agentic-building-blocks/prompts/prompt-engineering/role-prompting.md and 164 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
5 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-AGENT-TRUST-002, AAK-AGENT-TRUST-001, AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/claude.yml, .github/workflows/claude-code-review.yml, .github/workflows/deploy.yml · reported by agent-audit-kit
2 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-002, TOOL_ABUSE_UNDECLARED_NETWORK · Files: CLAUDE.md, /repo/repo/CLAUDE.md · reported by agent-audit-kit, cisco-skill-scanner

In installed code — never dismissed

These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.

52 MANIFEST_MISSING_LICENSE
Files: /repo/analyze-workspace/skill-snapshot/SKILL.md, /repo/.claude/skills/editing-hbr-articles/SKILL.md, /repo/.claude/skills/drafting-linkedin-posts/SKILL.md and 49 more · reported by cisco-skill-scanner
35 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/mcp-server/scripts/build-index.ts, /repo/plugins/multi-agent-example/scripts/article-to-docx.js, /repo/registry-template/tools/compose-registry.js and 4 more · reported by cisco-skill-scanner
26 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/registry-template/SKILL.md, /repo/plugins/SKILL.md and 23 more · reported by cisco-skill-scanner
8 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/.claude/hooks/publish-gate.sh, /repo/.claude/hooks/subagent-gate.sh, /repo/plugins/multi-agent-example/hooks/publish-gate.sh and 1 more · reported by cisco-skill-scanner
4 DATA_EXFIL_JS_NETWORK
Files: /repo/mcp-server/scripts/analytics-query.ts, /repo/mcp-server/src/dashboard.ts, /repo/mcp-server/src/index.ts and 1 more

Not reviewed

4 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-commands/hbr-article.md, skills-missing-telemetry-commands/hbr-article.md, skills-missing-telemetry-commands/hbr-article-strict.md and 1 more · Files: commands/hbr-article.md, commands/hbr-article-strict.md · reported by agentshield

What the review concluded

Artifact allows shell execution, file system access, and credential egress.

The artifact contains code that permits shell execution via command injection in `registry-lib.js`. It also includes numerous instances of file system access, including data exfiltration, and file deletion capabilities across various files, such as `test-publish-gate.sh`. Additionally, there is code that enables credential access and network egress. These capabilities are present in multiple scripts and agent definitions.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/registry-template/tools/registry-lib.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/registry-template/tools/registry-lib.js · critical · reported by cisco-skill-scanner
agents-no-tools-agents/ai-news-researcher.md · agents/ai-news-researcher.md · high · reported by agentshield
agents-no-tools-agents/claude-research-daily.md · agents/claude-research-daily.md · high · reported by agentshield
agents-no-tools-agents/meeting-prep-researcher.md · agents/meeting-prep-researcher.md · high · reported by agentshield
agents-no-tools-agents/playbook-question-answerer.md · agents/playbook-question-answerer.md · high · reported by agentshield
· · high · reported by agentshield

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

Scan history

1 scan on record. Every scan's full results are retained immutably for 24 months.

Completed	Composite	Change	Scanners	Status
Aug 21, 2026	Scan Halted	—	agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable	rejected

Per-scanner history:

AI review of these findings

Upheld as real: 245
Dismissed as false positives: 470
Not reviewed: 4

Out of 719 findings across every scanner that examined this package. 1 of 3 findings rated critical by their scanner was among the dismissals.

Not reviewed is not the same as clean. Those 4 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

Why those were dismissed

284 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: FILE_MAGIC_MISMATCH, MANIFEST_MISSING_LICENSE · Files: /repo/registry-template/tools/fixtures/valid-bundle/registry/workflows/third-workflow.md, /repo/registry-template/tools/fixtures/broken/multiline-frontmatter/registry/workflows/first-workflow.md, /repo/registry-template/tools/fixtures/broken/double-claim/registry/workflows/second-workflow.md and 272 more · reported by cisco-skill-scanner
179 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, FILE_MAGIC_MISMATCH, SOCIAL_ENG_ANTHROPIC_IMPERSONATION and 4 more · Files: src/content/docs/llms-full.txt, src/content/docs/ai-workflow-framework/deconstruct.md, src/content/docs/agentic-building-blocks/prompts/prompt-engineering/role-prompting.md and 164 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
5 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-AGENT-TRUST-002, AAK-AGENT-TRUST-001, AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/claude.yml, .github/workflows/claude-code-review.yml, .github/workflows/deploy.yml · reported by agent-audit-kit
2 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-002, TOOL_ABUSE_UNDECLARED_NETWORK · Files: CLAUDE.md, /repo/repo/CLAUDE.md · reported by agent-audit-kit, cisco-skill-scanner

In installed code — never dismissed

52 MANIFEST_MISSING_LICENSE
Files: /repo/analyze-workspace/skill-snapshot/SKILL.md, /repo/.claude/skills/editing-hbr-articles/SKILL.md, /repo/.claude/skills/drafting-linkedin-posts/SKILL.md and 49 more · reported by cisco-skill-scanner
35 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/mcp-server/scripts/build-index.ts, /repo/plugins/multi-agent-example/scripts/article-to-docx.js, /repo/registry-template/tools/compose-registry.js and 4 more · reported by cisco-skill-scanner
26 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/registry-template/SKILL.md, /repo/plugins/SKILL.md and 23 more · reported by cisco-skill-scanner
8 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/.claude/hooks/publish-gate.sh, /repo/.claude/hooks/subagent-gate.sh, /repo/plugins/multi-agent-example/hooks/publish-gate.sh and 1 more · reported by cisco-skill-scanner
4 DATA_EXFIL_JS_NETWORK
Files: /repo/mcp-server/scripts/analytics-query.ts, /repo/mcp-server/src/dashboard.ts, /repo/mcp-server/src/index.ts and 1 more

Not reviewed

4 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-commands/hbr-article.md, skills-missing-telemetry-commands/hbr-article.md, skills-missing-telemetry-commands/hbr-article-strict.md and 1 more · Files: commands/hbr-article.md, commands/hbr-article-strict.md · reported by agentshield

What the review concluded

Artifact allows shell execution, file system access, and credential egress.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/registry-template/tools/registry-lib.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/registry-template/tools/registry-lib.js · critical · reported by cisco-skill-scanner
agents-no-tools-agents/ai-news-researcher.md · agents/ai-news-researcher.md · high · reported by agentshield
agents-no-tools-agents/claude-research-daily.md · agents/claude-research-daily.md · high · reported by agentshield
agents-no-tools-agents/meeting-prep-researcher.md · agents/meeting-prep-researcher.md · high · reported by agentshield
agents-no-tools-agents/playbook-question-answerer.md · agents/playbook-question-answerer.md · high · reported by agentshield
· · high · reported by agentshield

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

handsonai

Install

Per-scanner reports

Scanners that examined this package (5)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

Scanners that did not run on this package (6)

capslock

nerlo-multi-source

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at

Install

Per-scanner reports

Scanners that examined this package (5)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

Scanners that did not run on this package (6)

capslock

nerlo-multi-source

Composite scoreOne view among many — the per-scanner reports above are primaryScan Halted

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at