dev-feature
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the local repository and documentation, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: The skill reads repository code files and project-specific documentation located at
docs/knowledge/INDEX.mdto inform implementation plans. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers when interpolating codebase content into the agent's context.
- Capability inventory: The skill has the ability to write to the filesystem, execute git commands (
git status), and run project-defined test and lint commands. - Sanitization: No explicit sanitization or validation logic is defined for the content read from the project files before processing.
- [COMMAND_EXECUTION]: The skill performs shell command execution to facilitate the development workflow.
- Evidence: Step 4 of the workflow instructs the agent to execute
git status --short, iterate with focused tests, and run full test and lint commands. These are standard development operations scoped to the repository environment.
Audit Metadata