documentation-audit
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by scanning the project's source code and documentation files. Instructions embedded in these files could influence the agent's behavior while it creates or updates documentation.
- Ingestion points: The skill scans code and documentation files via find and grep.
- Boundary markers: No delimiters or warnings are provided to the agent to ignore instructions within the audited data.
- Capability inventory: The skill uses Write and Edit tools to modify files and generates reports for external platforms like GitHub.
- Sanitization: No sanitization or filtering of the extracted content is performed before processing.
- [COMMAND_EXECUTION]: The skill relies on shell commands including find, grep, sed, xargs, yq, and jq to perform its codebase discovery and validation tasks.
Audit Metadata