research-brief-action-engine

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists solely of markdown instructions and reference files for data processing. It does not include executable scripts, request tool permissions, or attempt to access restricted file paths or environment variables.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external data such as research articles, transcripts, and web links. This creates an attack surface for indirect prompt injection. However, the risk is mitigated by the lack of any actionable capabilities within the skill's environment. * Ingestion points: messy research inputs, links, videos, articles, transcripts. * Boundary markers: Absent. * Capability inventory: None detected across all files. * Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 02:44 PM
Security Audit — agent-trust-hub — research-brief-action-engine