The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external PR content, which may contain malicious instructions designed to manipulate the agent.
Ingestion points: The skill retrieves metadata, comments, and reviews from GitHub using gh pr view as described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to isolate or ignore instructions contained within the fetched PR data.
Capability inventory: The skill can execute shell commands via the gh CLI, perform file system modifications to address CI failures or merge conflicts, and push code to repositories.
Sanitization: The skill does not implement specific sanitization or filtering for the ingested PR content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) for viewing PR state and checking status. While this is standard for its intended purpose, it involves the execution of external binaries with parameters derived from the PR environment.

babysit