pmf-market-research

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses standard agent capabilities including file discovery (Glob), sub-agent management (Task), and web data retrieval (WebSearch) to perform its stated purpose. No patterns of credential theft, unauthorized communication, or persistence were found.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its processing of untrusted external content.
  • Ingestion points: Reads project narratives from local files and processes external data from WebSearch via sub-agents.
  • Boundary markers: No explicit markers are defined to isolate untrusted web content from agent instructions.
  • Capability inventory: The skill uses Glob, Task, WebSearch, and file system read/write operations.
  • Sanitization: No explicit sanitization or validation of retrieved external content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 01:53 PM
Security Audit — agent-trust-hub — pmf-market-research