skills/backnotprop/bro/facts/Gen Agent Trust Hub

facts

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill consists of prompt instructions and metadata without any associated scripts or dangerous tool configurations.- [PROMPT_INJECTION]: The skill processes conversation history and planning data, which constitutes an indirect prompt injection surface. This is evaluated as safe due to the complete lack of exploitable sinks. * Ingestion points: Recent efforts and discussion history (SKILL.md). * Boundary markers: Not present. * Capability inventory: None. * Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 12:02 AM
Security Audit — agent-trust-hub — facts