codebase-wiki
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands including git, ls, cat, and grep for surveying the codebase and managing documentation freshness. These are standard development operations and do not involve high-risk commands or unauthorized access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase to generate wiki content, creating an attack surface for indirect prompt injection.
- Ingestion points: The entire codebase including manifests, source files, and existing documentation.
- Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded in the source code.
- Capability inventory: The agent has access to file-writing tools (write, edit) and shell execution (exec, Bash).
- Sanitization: The instructions advise omitting secrets in public mode but do not specify sanitization or escaping for general content.
Audit Metadata