The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted code from a repository. This creates a surface where instructions hidden within code comments or string literals could attempt to influence the agent's analysis or output.
Ingestion points: Local source files identified through the git diff command in SKILL.md.
Boundary markers: None explicitly defined to separate untrusted code from the analysis instructions.
Capability inventory: Employs Bash, Read, Grep, and Glob tools to inspect and process the codebase.
Sanitization: No specific filtering or escaping is applied to the analyzed content before it is processed by the agent.

code-reviewer