brief-generator

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided campaign details and local narrative files to generate briefs, creating a theoretical surface for indirect injection. However, this is consistent with its primary purpose and carries minimal risk.
  • Ingestion points: User inputs and local memory files (narrative.json, claims.json).
  • Boundary markers: The skill uses structured templates but does not define explicit delimiters for untrusted input.
  • Capability inventory: File-writing to the local memory directory and execution of a local event-logging script (registry-events.py).
  • Sanitization: No explicit sanitization of the input data is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:29 PM
Security Audit — agent-trust-hub — brief-generator