bdi-mental-states

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external RDF context to form agent beliefs, which creates a surface for indirect prompt injection where untrusted external data could influence the agent's mental states or reasoning logic.
  • Ingestion points: External RDF context (referenced in SKILL.md under Activation and Phase 1 sections).
  • Boundary markers: None mentioned; the patterns do not specify delimiters to separate untrusted data from the reasoning logic.
  • Capability inventory: The skill outlines processes for mental state deliberation, goal-directed planning, and augmenting LLM generation (Logic Augmented Generation).
  • Sanitization: No explicit sanitization or validation of the content within the RDF triples is described beyond basic semantic consistency checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 01:30 PM