The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs multiple shell operations using git and the GitHub CLI (gh). It executes commands for repository status checks, branch management, code commits, and pushing changes to remote branches. It also executes repository-specific tests and linters during the verification step.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through pull request comments. It reads input from human and bot reviewers and uses this data to decide on code changes and response content.\n
Ingestion points: The skill fetches review threads, summary bodies, and top-level conversation comments using gh api and GraphQL queries as described in Step 2 of SKILL.md.\n
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the content of PR comments as untrusted or to ignore embedded instructions.\n
Capability inventory: The agent has the ability to write to the file system, commit changes, and push to the remote repository. It also executes locally defined tests and linters.\n
Sanitization: There is no evidence of sanitization or filtering of the comment content before it influences the agent's actions or code generation.

fix-review