skills/gdewitte/agentic/grilling/Gen Agent Trust Hub

grilling

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected in the analyzed files. The instructions focus on establishing a shared understanding through one-by-one questioning.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to explore the environment (filesystem, tools) for facts, which creates an indirect prompt injection surface if those external sources are manipulated.
  • Ingestion points: Local filesystem and environmental tools referenced in SKILL.md.
  • Boundary markers: Absent; the skill does not define markers to separate data from instructions when reading facts.
  • Capability inventory: Uses default filesystem and tool exploration capabilities.
  • Sanitization: No validation or sanitization routines are specified for facts retrieved from the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 02:44 PM
Security Audit — agent-trust-hub — grilling