product-owner

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates data from untrusted local files into its processing flow while possessing significant capabilities.
  • Ingestion points: The skill dynamically discovers and reads content from docs/business-features/*/README.md, project-structure-reference.md, and other project documentation files using the Glob and Read tools.
  • Boundary markers: There are no defined delimiters or instructions to ignore potential commands within the ingested project documentation, allowing embedded instructions to potentially influence the agent's behavior.
  • Capability inventory: The skill is configured to use powerful tools including Write, Edit, Bash, and TaskCreate across its operation files.
  • Sanitization: The instructions do not specify any validation, escaping, or sanitization of the content read from the project files before it is processed or used to generate new artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:03 PM