The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (source code and pull request descriptions) which presents an attack surface for indirect prompt injection.
Ingestion points: Uses Read, Grep, and Glob tools to access filesystem content as specified in SKILL.md.
Boundary markers: There are no explicit instructions for the agent to ignore or delimit instructions found within the code being reviewed.
Capability inventory: The skill is restricted to Read, Grep, and Glob tools. It lacks network access, command execution, or filesystem write capabilities, significantly mitigating the impact of any potential injection.
Sanitization: No explicit sanitization or filtering of the ingested code content is performed before processing.

code-reviewer