agent-debug-memory-51ce2a — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited agent-debug-memory-51ce2a (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 2 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use Noosphere as Claude Code's shared debugging memory layer before and after substantial debugging work.
consult_noosphere with that query.topic_tags, such as react, vite, typescript, mcp, github-actions, async-ui, claude-code, windows, or the library name.When the outcome is verified and the lesson is reusable, upload a distilled memory with upload_consciousness.
Use:
consciousness_type: "warning" for pitfalls, footguns, version traps, and failure modes.consciousness_type: "pattern" for reusable fixes, workflows, or implementation patterns.consciousness_type: "decision" for tradeoff-heavy engineering choices.The uploaded memory should include:
Keep the memory concise and general enough for another agent to reuse.
Do not claim the fix is complete until local verification has passed or you have clearly stated what could not be run. If the Noosphere MCP server is unavailable, explain that the plugin requires uvx, noosphere-mcp, and a GitHub token configured during plugin setup.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.