The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches external content from GitHub.com (specifically .diff files) based on the user-provided PR URL. GitHub is recognized as a well-known and trusted service.
[COMMAND_EXECUTION]: The instructions recommend using the grep utility to process large diff files, which involves executing system-level commands to filter text content.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external GitHub pull requests. Maliciously crafted code comments or documentation within a PR diff could attempt to influence the agent's summary or the behavior of the downstream /review-ci and /review-ui skills.
Ingestion points: Fetches raw diff content from the URL provided in the PR_URL argument (e.g., https://github.com/.../pull/190.diff).
Boundary markers: The skill lacks explicit boundary markers or system instructions to ignore potential commands embedded within the fetched diff content.
Capability inventory: The skill uses grep for data processing and acts as an orchestrator for other automated review skills.
Sanitization: There is no evidence of sanitization, filtering, or escaping of the diff content before it is processed or passed to subsequent skills.

review-pr