Loading the registry…
Local-first YouTube AI CLI: download, transcribe (captions -> whisper), embed in LanceDB, discover subscriptions, and summarize/highlight/Q&A.
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.
327 critical findings reported by cisco-skill-scanner, agent-audit-kit, 3 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/dasein108/yt-mem-ai, 426 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- yt-mem-ai
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
0 findings · 0.5s
v2.0.11
61 findings · 10.4s
v0.3.26
337 findings · 3.2s
v0.1.0
0 findings · 27.4s
v0.1.0
19 findings · 27.4s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 11.0s
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 3, 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 417 findings across every scanner that examined this package. 323 of 327 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 7 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.
324 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, PIPELINE_TAINT_FLOW · Files: AGENTS.md, CLAUDE.md, /repo/CLAUDE.md · reported by agent-audit-kit, cisco-skill-scanner
18 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-pipe-to-shell, PIPELINE_TAINT_FLOW, YARA_prompt_injection_unicode_steganography and 4 more · Files: /repo/CLAUDE.md, /repo/docs/superpowers/plans/2026-07-25-repo-split-engine-desktop.md, /repo/docs/demo/codex-install.gif and 5 more · reported by nerlo-install-instruction, cisco-skill-scanner, agent-audit-kit
3 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/publish-pypi.yml · reported by agent-audit-kit
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.
13 MANIFEST_MISSING_LICENSE
Files: /repo/skills/yt-agent/SKILL.md, /repo/skills/yt/SKILL.md, /repo/SKILL.md and 10 more · reported by cisco-skill-scanner
11 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/skills/yt-agent/SKILL.md, /repo/SKILL.md, /repo/skills/SKILL.md and 8 more · reported by cisco-skill-scanner
8 PIPELINE_TAINT_FLOW
Files: /repo/install.sh, /repo/SKILL.md, /repo/integrations/README.md and 2 more · reported by cisco-skill-scanner
6 HIDDEN_DATA_FILE
Files: /repo/integrations/codex/.codex-plugin/plugin.json, /repo/integrations/cursor/.cursor-plugin/plugin.json · reported by cisco-skill-scanner
6 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md, /repo/install.sh, /repo/integrations/README.md · reported by nerlo-install-instruction
3
7 The model did not answer for these findings.
Rules: opt.nerlo-rules.nerlo-install-fetch-raw-then-run, PIPELINE_TAINT_FLOW · Files: /repo/docs/superpowers/plans/2026-07-25-repo-split-engine-desktop.md, /repo/docs/superpowers/plans/SKILL.md · reported by nerlo-install-instruction, cisco-skill-scanner
Critical risks: shell execution, credential exposure, and network egress.
The artifact contains critical findings related to shell execution via `eval` in `yt_mem_ai/mcp_server.py` and compound fetch-and-execute patterns in `integrations/PROMPT.md` and `integrations/SKILL.md`. High severity findings indicate potential command injection from user input in `install.sh`, exposure of secrets in `yt_mem_ai/config.py`, and DNS rebinding risks in `pyproject.toml`. These capabilities could allow arbitrary code execution, access to sensitive information, and network manipulation.
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.
Files: /repo/integrations/PROMPT.md, /repo/integrations/SKILL.md · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/README.md, /repo/install.ps1, /repo/integrations/README.md · reported by nerlo-install-instruction
2 AAK-DNS-REBIND-002
Files: pyproject.toml · reported by agent-audit-kit
2 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json, integrations/claude-code/.claude-plugin/marketplace.json · reported by agent-audit-kit
2 AAK-MCP-007
Files: integrations/cursor/mcp.json · reported by agent-audit-kit
2 AAK-SECRET-004
Files: yt_mem_ai/config.py · reported by agent-audit-kit
2 COMMAND_INJECTION_USER_INPUT
Files: /repo/install.sh · reported by cisco-skill-scanner
1 AAK-MCP-005
Files: integrations/cursor/mcp.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: yt_mem_ai/mcp_server.py · reported by agent-audit-kit
1 COMMAND_INJECTION_EVAL
Files: /repo/yt_mem_ai/mcp_server.py · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/integrations/cursor/README.md · reported by nerlo-install-instruction
Showing 25 of 26; the rest are in the per-scanner reports above.