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

205

Dismissed as false positives

Not reviewed

Out of 218 findings across every scanner that examined this package. None of the 3 findings rated critical by their scanner were dismissed.

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.

7 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-GHA-IMMUTABLE-001 · Files: .github/workflows/ci.yml, .github/workflows/release.yml · reported by agent-audit-kit
4 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-003, AAK-AGENT-002, AAK-AGENT-004 · Files: CLAUDE.md · reported by agent-audit-kit
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md · reported by 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.

3 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/build-mcpb.mjs · reported by cisco-skill-scanner
2 AAK-MCP-018
Files: src/prompts.ts, src/index.ts · reported by agent-audit-kit
2 AAK-MCPFRAME-001
Files: src/index.ts, src/oauth/entra-proxy.ts · reported by agent-audit-kit
2 AAK-OAUTH-007
Files: src/index.ts, src/oauth/entra-proxy.ts · reported by agent-audit-kit
2 DATA_EXFIL_JS_NETWORK
Files: /repo/src/oauth/entra-proxy.ts · reported by cisco-skill-scanner
2 GHSA-26pp-8wgv-hjvm
Files: /repo/package-lock.json, package-lock.json · reported by osv-scanner, trivy

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

1 CVE-2026-75975
Files: package-lock.json · reported by trivy

What the review concluded

Critical command injection and high-severity supply chain vulnerabilities detected.

The artifact contains critical command injection vulnerabilities in `build-mcpb.mjs` that could lead to shell execution. Permissive permissions in configuration files like `.claude/settings.local.json` and `settings.local.json` may allow unauthorized shell execution or Docker builds. Additionally, the artifact may transmit secrets over the network from `entra-proxy.ts`, and numerous high-severity vulnerabilities are present in included dependencies.

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/scripts/build-mcpb.mjs · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/scripts/build-mcpb.mjs · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/scripts/build-mcpb.mjs · critical · reported by cisco-skill-scanner
AAK-TRUST-004 · .claude/settings.local.json · high · reported by agent-audit-kit
AAK-MCP-STATELESS-001 · src/index.ts · high · reported by agent-audit-kit
permissions-no-deny-list · .claude/settings.local.json · high · reported by agentshield
permissions-permissive-Bash(docker build:*) · .claude/settings.local.json · high · reported by agentshield

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

AI review of these findings

Upheld as real

205

Dismissed as false positives

Not reviewed

Out of 218 findings across every scanner that examined this package. None of the 3 findings rated critical by their scanner were dismissed.

Why those were dismissed

7 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-GHA-IMMUTABLE-001 · Files: .github/workflows/ci.yml, .github/workflows/release.yml · reported by agent-audit-kit
4 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-003, AAK-AGENT-002, AAK-AGENT-004 · Files: CLAUDE.md · reported by agent-audit-kit
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md · reported by cisco-skill-scanner

In installed code — never dismissed

3 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/build-mcpb.mjs · reported by cisco-skill-scanner
2 AAK-MCP-018
Files: src/prompts.ts, src/index.ts · reported by agent-audit-kit
2 AAK-MCPFRAME-001
Files: src/index.ts, src/oauth/entra-proxy.ts · reported by agent-audit-kit
2 AAK-OAUTH-007
Files: src/index.ts, src/oauth/entra-proxy.ts · reported by agent-audit-kit
2 DATA_EXFIL_JS_NETWORK
Files: /repo/src/oauth/entra-proxy.ts · reported by cisco-skill-scanner
2 GHSA-26pp-8wgv-hjvm
Files: /repo/package-lock.json, package-lock.json · reported by osv-scanner, trivy

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

1 CVE-2026-75975
Files: package-lock.json · reported by trivy

What the review concluded

Critical command injection and high-severity supply chain vulnerabilities detected.

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/scripts/build-mcpb.mjs · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/scripts/build-mcpb.mjs · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/scripts/build-mcpb.mjs · critical · reported by cisco-skill-scanner
AAK-TRUST-004 · .claude/settings.local.json · high · reported by agent-audit-kit
AAK-MCP-STATELESS-001 · src/index.ts · high · reported by agent-audit-kit
permissions-no-deny-list · .claude/settings.local.json · high · reported by agentshield
permissions-permissive-Bash(docker build:*) · .claude/settings.local.json · high · reported by agentshield

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

Completed	Composite	Change	Scanners	Status
Sep 13, 2026	Flagged31	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable	completed
Sep 3, 2026	Flagged31	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable	completed
Aug 2, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete	rejected
Jul 30, 2026	Scan Halted	—	cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete	rejected
Jul 28, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete	rejected

bookstack-mcp

Install

Per-scanner reports

Scanners that examined this package (8)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

nerlo-multi-source

trivy

osv-scanner

Scanners that did not run on this package (3)

capslock

trivy (image)

govulncheck

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Install

Per-scanner reports

Scanners that examined this package (8)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

nerlo-multi-source

trivy

osv-scanner

Scanners that did not run on this package (3)

capslock

trivy (image)

govulncheck

Composite scoreOne view among many — the per-scanner reports above are primaryFlagged31

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at