refactoring
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the user-provided codebase, creating a surface for indirect prompt injection.
- Ingestion points: The workflow in
SKILL.md(Step 1) requires the agent to inspect codebase files, repository instructions, and test files. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers when reading these external files.
- Capability inventory: The agent is authorized to modify files and execute shell-based verification commands/tests within the user environment.
- Sanitization: No sanitization or validation logic is specified for the content retrieved from the target files before it is processed or used to influence agent actions.
Audit Metadata