The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from the local filesystem to populate the release checklist, which creates a surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Reads project context from CLAUDE.md, milestone data from production/milestones/, and scans the codebase for TODO, FIXME, and HACK comments.
Boundary markers: Absent. The instructions do not define delimiters or provide guidance to the agent to ignore instructions embedded within the processed project files.
Capability inventory: The skill uses Read, Glob, Grep, and Write tools to interact with the project environment.
Sanitization: Absent. Content retrieved from the codebase is interpolated directly into the markdown report without validation or escaping.

release-checklist