prd
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied feature descriptions to create Markdown files, which introduces a surface for indirect prompt injection attacks.
- Ingestion points: The agent receives a feature description and feature name from the user as primary inputs in the 'Step 1: Clarifying Questions' phase.
- Boundary markers: The instructions do not specify any delimiters (such as triple quotes or XML tags) or provide explicit guidance for the agent to ignore potentially malicious instructions embedded within the user's input.
- Capability inventory: The skill has the capability to write files to the local filesystem at the path 'tasks/prd-[feature-name].md'.
- Sanitization: There is no requirement for the agent to sanitize the 'feature-name' or the content of the feature description, which could potentially lead to path traversal attempts or the injection of malicious Markdown or commands into the resulting file.
Audit Metadata