The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using git and the GitHub CLI (gh) to fetch diffs, view PR details, and post review comments. It also uses npx to run a consolidation tool.
[EXTERNAL_DOWNLOADS]: The skill uses npx @ericrisco/rsc to execute a utility for consolidating review reports. This package is authored by the same vendor as the skill.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including PR titles, bodies, and code diffs, which could contain malicious instructions. | Ingestion points: Data is gathered via gh pr diff, gh pr view, and git diff commands. | Boundary markers: There are no specific instructions or delimiters mentioned to segregate untrusted PR content from the agent's internal logic. | Capability inventory: The agent can execute shell commands, perform network requests to the GitHub API, and modify the filesystem when the --fix option is used. | Sanitization: No explicit sanitization or filtering of the incoming PR data is performed before processing.

code-review