The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub pull request comments to automate code modifications and command execution.
Ingestion points: External comments are fetched via gh api in Step 2 of SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to separate reviewer instructions from agent guidelines during processing.
Capability inventory: The skill uses Write and Edit tools to modify source code and Bash to perform git commit and git push operations.
Sanitization: There is no mention of sanitizing or filtering the body of comments before the agent interprets them as actionable tasks.

git-pr-feedback