prd-generation

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external sources without sufficient isolation.
  • Ingestion points: Step 1 in SKILL.md describes ingesting "upstream artifacts" (such as output from problem-framing or user-modeling) and "raw input" from the user.
  • Boundary markers: The instructions lack explicit delimiters or specific directives to treat the ingested data solely as data and to ignore any embedded instructions.
  • Capability inventory: The skill utilizes the Write tool to automatically save the generated PRD to the filesystem at design/05-prd.md.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the ingested content to prevent malicious or malformed instructions from affecting the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:35 AM