faion-user-researcher

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and process untrusted external data, creating a surface for indirect prompt injection attacks.
  • Ingestion points: The skill explicitly instructs the agent to check and analyze external data sources including .aidocs/product_docs/interview-notes/, support tickets, customer reviews, and web-searched content (as defined in SKILL.md and pain-point-research/README.md).
  • Boundary markers: No specific boundary markers or 'ignore embedded instructions' warnings are implemented in the templates to differentiate between instruction and data.
  • Capability inventory: The skill allows the use of WebSearch, WebFetch, Read, and Write tools, which could be leveraged to exfiltrate processed data if a malicious instruction is encountered in a research source.
  • Sanitization: No sanitization or validation logic is defined for the external content before it is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:24 PM