The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Reads PRDs, Technical Specifications, Task lists, and source code files from the project repository (SKILL.md Steps 1 & 2).
Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the files being read.
Capability inventory: The skill is authorized to execute shell commands (git, test suites, static analysis), write files (reports and fix tasks), and delete temporary directories (SKILL.md Steps 2, 6, 8, 9).
Sanitization: No sanitization or validation of the ingested file content is mentioned before the data is processed by the AI.
[COMMAND_EXECUTION]: The skill performs shell command execution as a core part of its code analysis and verification functionality.
Evidence: Uses git status, git diff, and git rev-parse to analyze the repository state (SKILL.md Step 2).
Evidence: Dynamically resolves and executes the project's own test suite and static analysis tools based on project configuration (SKILL.md Step 6).

do-execute-review