The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run git diff for gathering source code changes and executes a local bash script scripts/review-ai-residuals.sh to scan for potential security vulnerabilities and temporary code artifacts. These operations are consistent with its primary function as a review tool.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to its processing of untrusted external content.
Ingestion points: Analyzes data directly from git diff output and the Plans.md file.
Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted code/text from the agent's internal instructions.
Capability inventory: The skill has access to powerful tools including Bash, Task, Read, Grep, and Glob.
Sanitization: No logic is provided to sanitize or validate the content of the reviewed data before it is processed by the AI.

harness-review