prd-to-appspec
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided Product Requirements Documents (PRDs). This creates a surface for indirect prompt injection, where malicious instructions embedded in a PRD could potentially manipulate the agent's behavior during the transformation process. Evidence Chain: 1. Ingestion points: The entire PRD file is read into the agent's context as specified in
workflows/convert-prd.md(Step 1). 2. Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the PRD content as data rather than instructions. 3. Capability inventory: The skill utilizes filesystem read and write capabilities to process documents and save the output toprompts/app_spec.txt. 4. Sanitization: No sanitization or validation of the input text is performed to filter out potentially malicious prompt segments. - [NO_CODE]: The skill consists primarily of markdown-based instructions and metadata. It does not contain executable scripts or binary files, which significantly reduces the direct attack surface for traditional malicious payloads.
Audit Metadata