anatomia-cc
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a knowledge base and design tool. Its primary function is to guide the user through a decision tree for project architecture within the Claude Code platform.
- [COMMAND_EXECUTION]: The skill contains various shell script templates and CLI command examples (e.g.,
claude mcp addorjqcommands inassets/esqueleto-hook.md). These are static pedagogical examples intended for the user to implement and are not executed by the skill during its own lifecycle. - [CREDENTIALS_UNSAFE]: The documentation includes strings resembling API keys (e.g.,
sk_live_a1b2...). These are explicitly used as examples of anti-patterns to teach the user which practices are insecure and should be avoided. No real or functional credentials are leaked or stored. - [EXTERNAL_DOWNLOADS]: The skill references well-known technology services and official repositories (e.g., Anthropic's Agent SDK, GitHub, Slack, and Notion) as examples of standard integrations. These references are neutral and point to trusted industry providers.
- [NO_CODE]: The skill consists exclusively of Markdown documentation, templates, and JSON evaluation files. It does not include any hidden scripts, binaries, or obfuscated payloads.
Audit Metadata