create-plan
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external project files (such as README.md, docs, and source code) which could contain adversarial instructions.
- Ingestion points: The workflow involves scanning project context, including
README.md,docs/,CONTRIBUTING.md, and other relevant files. - Boundary markers: The instructions do not define specific delimiters or "ignore" markers for content read from these files.
- Capability inventory: The skill explicitly mandates a "read-only mode" and forbids writing or updating files. It contains no commands for network access or code execution.
- Sanitization: No specific sanitization or filtering of the ingested file content is mentioned.
- Result: Because the skill is strictly read-only and only produces a text-based plan, the risk of successful prompt injection through these files is negligible.
Audit Metadata