Loading the registry…
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
269 critical findings reported by cisco-skill-scanner, agent-audit-kit, 128 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/commet/argus, 1696 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- argus
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
7 findings · 2.8s
v2.0.11
1404 findings · 201.5s
v0.3.26
205 findings · 117.4s
v0.1.0
80 findings · 252.2s
v0.1.0
0 findings · 252.3s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 12.0s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | rejected |
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.
Out of 1,696 findings across every scanner that examined this package. 135 of 269 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 5 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
431 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: COMMAND_INJECTION_JS_CHILD_PROCESS, YARA_credential_harvesting_generic, YARA_script_injection_generic and 11 more · Files: /repo/argus-mcp/src/lib/__tests__/cross-surface-contract.test.ts, /repo/argus-plugin-v2/scripts/ask-budget.test.mjs, /repo/argus-plugin-v2/scripts/decision-ledger.test.mjs and 84 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral
99 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-001, AAK-AGENT-003, agents-prompt-extraction-1061 and 3 more · Files: CLAUDE.md, /repo/.github/SKILL.md · reported by agent-audit-kit, agentshield, cisco-skill-scanner
36 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_generic, AAK-HEALTHCARE-AI-005, AAK-HEALTHCARE-AI-004 and 3 more · Files: /repo/.github/SECURITY.md, /repo/.github/SKILL.md, docs/AGENT-ARCHITECTURE-FOUNDATIONAL-2026-07-05.md and 16 more · reported by cisco-skill-scanner, agent-audit-kit
1 Placeholder value — The matched literal is a placeholder or example — the kind of value a scanner reads as a secret and a human reads as a blank to fill in.
Rules: YARA_credential_harvesting_generic · Files: /repo/src/lib/__tests__/jcr-j8-portability-erasure.test.ts · reported by cisco-skill-scanner
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.
604 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/argus-mcp/dogfood/run.mjs, /repo/argus-mcp/evals/ambient-picker.mjs, /repo/argus-mcp/evals/answer-time.mjs and 83 more · reported by cisco-skill-scanner
116 DATA_EXFIL_JS_NETWORK
Files: /repo/argus-mcp/argus-decision-mcp-2.0.1.tgz!/package/dist/index.js, /repo/argus-mcp/evals/anthropic.mjs, /repo/argus-mcp/src/lib/push-account.ts and 45 more · reported by cisco-skill-scanner
96 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/argus-mcp/evals/ambient-picker.mjs, /repo/argus-mcp/evals/answer-time.mjs, /repo/argus-mcp/evals/architecture-review.mjs and 23 more · reported by cisco-skill-scanner
58 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/argus-mcp/evals/anthropic.mjs, /repo/argus-mcp/src/lib/push-account.ts, /repo/argus-plugin-v2/evals/detection/auto-detect-eval.mjs and 39 more · reported by nerlo-behavioral
35 AAK-HEALTHCARE-AI-005
Files: argus-plugin-v2/CHANGELOG.md, argus-plugin-v2/README.md, scripts/sim/REPORT.md and 32 more
5 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: YARA_credential_harvesting_generic, AAK-SECRET-002, AAK-SECRET-001 · Files: /repo/src/app/api/llm/__tests__/validation.test.ts, src/app/api/llm/__tests__/validation.test.ts · reported by cisco-skill-scanner, agent-audit-kit
Artifact has critical command injection and credential access risks.
The artifact contains numerous critical command injection vulnerabilities, allowing for shell execution in files like `argus-mcp/evals/_codex-bin.mjs` and `argus-mcp/evals/ambient-picker.mjs`. It also exhibits critical credential access risks, specifically in `src/app/api/llm/__tests__/validation.test.ts`. Additionally, there are high-severity findings related to secrets being sent over network egress.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
29 AAK-SECRET-004
Files: scripts/uiux-loop/quality-refute.ts, scripts/uiux-loop/score-harness.ts, scripts/uiux-loop/step0-probe.ts and 25 more · reported by agent-audit-kit
29 MANIFEST_MISSING_LICENSE
Files: /repo/argus-plugin-v2/skills/history/SKILL.md, /repo/argus-plugin-v2/skills/settings/SKILL.md, /repo/argus-plugin-v2/skills/check/SKILL.md and 26 more · reported by cisco-skill-scanner
22 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/argus-mcp/SKILL.md, /repo/argus-plugin-v2/SKILL.md and 19 more · reported by cisco-skill-scanner
21 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/argus-mcp/evals/anthropic.mjs, /repo/argus-plugin-v2/evals/detection/auto-detect-eval.mjs, /repo/argus-plugin-v2/evals/detection/mcp-firing-sim.mjs and 14 more · reported by nerlo-behavioral
14 HIDDEN_DATA_FILE
Files: /repo/.design-templates/design_handoff_argus_films/source/ArgusWorkspace.dc.html, /repo/scripts/sim/.build/harness-probe.mjs, /repo/.design-templates/design_handoff_argus_films/source/ArgusHeroDemo.dc.html and 7 more · reported by cisco-skill-scanner
13 COMMAND_INJECTION_EVAL
Files: /repo/scripts/sim/retest-capture-mobile.mjs, /repo/scripts/sim/retest-capture-rn.mjs, /repo/scripts/sim/retest-capture.mjs and 3 more · reported by cisco-skill-scanner
13 LOW_ANALYZABILITY
Files: /repo/scripts/dogfood/experience, /repo/argus-mcp/spikes/p0, /repo/argus-mcp and 10 more · reported by cisco-skill-scanner
12 AAK-MCP-STDIO-CMD-INJ-002
Files: argus-mcp/evals/discover.mjs, argus-mcp/evals/e2e-picker.mjs, argus-mcp/evals/unreadable-ledger.mjs and 9 more · reported by agent-audit-kit
10 AAK-HEALTHCARE-AI-004
Files: argus-mcp/CHANGELOG.md, argus-plugin-v2/CHANGELOG.md, argus-plugin-v2/README.md and 7 more · reported by agent-audit-kit
7 FILE_MAGIC_MISMATCH
Files: /repo/argus-mcp/src/v2/ledger.ts, /repo/argus-mcp/src/v3/p5-gate.ts, /repo/argus-mcp/src/test-setup.ts and 1 more · reported by cisco-skill-scanner
6 YARA_prompt_injection_generic
Files: /repo/argus-plugin-v2/lib/workflows/scan.md, /repo/argus-plugin-v2/lib/workflows/SKILL.md, /repo/src/lib/persona-prompt.ts · reported by cisco-skill-scanner
4 OBFUSCATION_HEX_BLOB
Files: /repo/argus-mcp/argus-decision-mcp-2.0.1.tgz!/package/dist/index.js · reported by cisco-skill-scanner
4 UNANALYZABLE_BINARY
Files: /repo/public/voyage/voyage-film.mp4, /repo/public/voyage/voyage-film-mobile.mp4, /repo/argus-mcp/argus-decision-mcp-2.0.1.tgz · reported by cisco-skill-scanner
3 AAK-MCP-018
Files: argus-mcp/src/a0/account-connect.ts, argus-mcp/spikes/ambient-elicit/server-oob.mjs, argus-plugin-v2/scripts/push-webapp.js · reported by agent-audit-kit
3 ASSET_PROMPT_INJECTION
Files: /repo/argus-plugin-v2/evals/cases.json · reported by cisco-skill-scanner
3 EXCESSIVE_FILE_COUNT
Files: /repo/argus-mcp/., /repo/argus-plugin-v2/., /repo/. · reported by cisco-skill-scanner
3 YARA_prompt_injection_unicode_steganography
Files: /repo/public/images/brand/argus-v2/argus-canon.jpg, /repo/public/voyage/voyage-film-mobile.mp4 · reported by cisco-skill-scanner
2 ARCHIVE_FILE_DETECTED
Files: /repo/argus-mcp/argus-decision-mcp-2.0.1.tgz · reported by cisco-skill-scanner
2 BINARY_FILE_DETECTED
Files: /repo/public/voyage/voyage-film.mp4, /repo/public/voyage/voyage-film-mobile.mp4 · reported by cisco-skill-scanner
2 hooks-no-pretooluse
Files: settings.json, .claude/settings.json · reported by agentshield
2 MANIFEST_INVALID_NAME
Files: /repo/.design-templates/design_handoff_argus_films/SKILL.md, /repo/argus-plugin-v2/skills/_generated/SKILL.md · reported by cisco-skill-scanner
2 permissions-no-block
Files: settings.json, .claude/settings.json · reported by agentshield
2 YARA_code_execution_generic
Files: /repo/argus-mcp/src/lib/surfaces.ts · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-015
Files: argus-plugin-v2/scripts/push-webapp.js · reported by agent-audit-kit
1 AAK-SUPPLY-003
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 AAK-TAINT-001
Files: argus-mcp/src/a0/account-connect.ts · reported by agent-audit-kit
1 AAK-TASKS-003
Files: src/lib/hit-rate.ts · reported by agent-audit-kit
1 OVERSIZED_FILE
Files: /repo/public/voyage/voyage-film.mp4 · reported by cisco-skill-scanner
Showing 25 of 257; the rest are in the per-scanner reports above.