The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git diff commands to identify changed files and retrieve code for analysis. This is a core component of its intended functionality for reviewing code changes.
[PROMPT_INJECTION]: There is a surface for indirect prompt injection because the skill ingests untrusted data from git diff outputs. Malicious code or comments within the diff could theoretically attempt to influence the agent's summary or final verdict. 1. Ingestion points: Untrusted code changes gathered via git diff. 2. Boundary markers: None explicitly defined to isolate the diff data from instructions. 3. Capability inventory: Invokes analysis via scan and security_review tools. 4. Sanitization: No explicit sanitization or filtering of the diff content is mentioned before processing.

endor-review