skills/dmmulroy/.dotfiles/grilling/Gen Agent Trust Hub

grilling

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill's primary function is to facilitate a conversational interview process. No malicious code, safety bypasses, or obfuscated content were detected.\n- [NO_CODE]: The skill contains no executable scripts or binaries, consisting entirely of markdown instructions and metadata configuration.\n- [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection because it instructs the agent to lookup facts from its environment.\n
  • Ingestion points: Local filesystem and tool outputs (SKILL.md).\n
  • Boundary markers: Absent; the instructions do not specify markers to isolate environmental context.\n
  • Capability inventory: Mentions filesystem access and tool usage (SKILL.md).\n
  • Sanitization: Absent; the skill does not define validation or filtering of environmental data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 08:47 AM
Security Audit — agent-trust-hub — grilling