The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from an external issue tracker, creating a surface for indirect prompt injection. Ingestion points: The agent reads the body and metadata of 'map' and 'ticket' issues from the repository's tracker. Boundary markers: No delimiters or 'ignore' instructions are provided to separate user-controlled ticket content from agent instructions. Capability inventory: The agent possesses significant capabilities including shell command execution, file system access, and the ability to modify remote issue data. Sanitization: There is no evidence of validation or filtering for data retrieved from the tracker.
[COMMAND_EXECUTION]: The skill provides a shell command to search for and identify configuration files within the project structure. Evidence: ls */skills/*-engineer/TRACKER.md .*/skills/*-engineer/TRACKER.md 2/dev/null is used to locate the tracker definition file.

wayfinder