prd-generator
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to populate generated documentation.\n
- Ingestion points: The
scripts/generate_prd.shscript reads user input for several PRD fields including the problem statement and business goals.\n - Boundary markers: There are no boundary markers or directives within the generated markdown to distinguish user input from the template structure.\n
- Capability inventory: The skill possesses file-writing capabilities through the
scripts/generate_prd.shscript.\n - Sanitization: User input is not sanitized or escaped before being written to the output file, creating a surface for potentially malicious instructions to be embedded in the generated PRD.
Audit Metadata