The Agent Skills Directory

[SAFE]: No prompt injection or safety bypass instructions were detected in the skill instructions.
[SAFE]: File access is restricted to reading the codebase and upstream artifacts for discovery purposes and writing the resulting maps to the .context/ directory.
[SAFE]: Command execution is limited to standard development tools like git diff for incremental mapping, which is appropriate for the skill's stated purpose.
[SAFE]: The skill does not perform any network operations to non-whitelisted or suspicious external domains.
[SAFE]: Although the skill processes untrusted codebase data (potential Indirect Prompt Injection surface), its operations are limited to structural mapping rather than executing the content of the files it analyzes.

qa-map