The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code content from external PRs and branches, which could be used to host malicious instructions.
Ingestion points: The skill reads file paths and diff content using gh pr view, git log, and git diff as described in Step 1 and Step 2.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are provided to protect the agent's context.
Capability inventory: The skill requires access to the gh and git command-line tools to interact with repositories.
Sanitization: There is no sanitization of the data retrieved from the repository before it is analyzed by the AI.

diff-intake