Skills
skills/allinherog-star/ai-skills/ai-account-research/Gen Agent Trust Hub

ai-account-research

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing external, untrusted content from multiple sources.
  • Ingestion points: Defined in references/form-schema.json as materialText, materialUrl (external links), and materialFile (CSV/Excel files).
  • Boundary markers: No explicit prompt delimiters or safety warnings are implemented in the local instruction files.
  • Capability inventory: The skill performs network POST requests to the ai-skills.ai API via the scripts/run.py runner.
  • Sanitization: The local runner does not perform content sanitization; processing and safety filtering are handled server-side by the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:30 AM
Security Audit — agent-trust-hub — ai-account-research