gsd-map-codebase
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes external codebase content, which presents a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill reads files from the local codebase using
Glob,Grep, andReadtools, and loads project state from.planning/STATE.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are implemented to separate analyzed code from agent instructions.
- Capability inventory: The skill has access to
Bash(for command execution and git operations),Write(for creating documentation), andAgent(for parallel processing) tools. - Sanitization: The skill does not perform sanitization or validation on the content of the files it reads before passing them to analysis agents.
Audit Metadata