The Agent Skills Directory

[COMMAND_EXECUTION]: Employs dynamic context injection in the YAML frontmatter to execute git log. This is a benign operation used to gather necessary metadata for the retrospective.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting untrusted data from the git history and codebase search results.\n
Ingestion points: git log output and technical debt markers found via Grep across the codebase.\n
Boundary markers: Absent; no specific instructions are provided to ignore potentially malicious instructions within the commit messages or code comments.\n
Capability inventory: The skill is permitted to use Read, Glob, Grep, and Write tools to interact with the local filesystem.\n
Sanitization: No explicit sanitization or validation of input data is defined in the instructions.

retrospective