product-agent

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests untrusted user input (product ideas) and uses it to drive internal reasoning and external web searches.
  • Ingestion points: User-provided app ideas are ingested in SKILL.md to initiate the discovery analysis.
  • Boundary markers: The instructions do not define explicit delimiters or "ignore instructions" warnings for the user-supplied content.
  • Capability inventory: The skill utilizes WebSearch, WebFetch, and Write capabilities to perform market research and save analysis results.
  • Sanitization: No input validation or sanitization logic is specified for the user-provided data before it is processed by the agent or passed to search tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 01:19 PM
Security Audit — agent-trust-hub — product-agent