skills/marcioaltoe/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions without executable code, scripts, or external dependencies. It defines a persona for the agent to help users review plans.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions the agent to "explore the codebase" to answer questions. This creates an attack surface where untrusted data within the codebase (such as malicious instructions in comments) could influence the agent's behavior. However, this is a standard feature of codebase agents and is limited by the context of a design review.
  • Ingestion points: Local codebase (SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: None (standard agent tools assumed)
  • Sanitization: None
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 03:10 AM
Security Audit — agent-trust-hub — grill-me