faion-market-researcher

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses a vulnerability surface for indirect prompt injection because it ingests external, untrusted data to generate reports.\n
  • Ingestion points: Uses WebSearch and WebFetch to gather intelligence from the web as defined in SKILL.md and referenced research frameworks.\n
  • Boundary markers: The templates provided across the skill (e.g., in pricing-research/README.md) do not include explicit delimiters or instructions to ignore instructions embedded within the fetched data.\n
  • Capability inventory: The skill is authorized in SKILL.md to use Write tools to save research results to the local filesystem in .aidocs/product_docs/.\n
  • Sanitization: No sanitization or filtering logic for external content is included in the methodologies.\n- No Code (SAFE): The skill consists entirely of Markdown documentation and templates. No executable Python or Node.js scripts were found in any of the 112 files analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM