skills/taecontrol/skills/grilling/Gen Agent Trust Hub

grilling

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied plans, decisions, or ideas, creating a surface for indirect prompt injection when these inputs are used to drive tool operations.
  • Ingestion points: User-provided text describing a plan, decision, or idea (SKILL.md).
  • Boundary markers: The instructions lack explicit delimitation or boundary markers to separate user-provided content from instructions given to the agent or sub-agents.
  • Capability inventory: The skill explicitly directs the agent to dispatch sub-agents or tools to find facts from the filesystem and environment based on the user's input (SKILL.md).
  • Sanitization: There are no instructions for sanitizing or validating user input before it is processed or used to trigger tool executions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 11:53 PM
Security Audit — agent-trust-hub — grilling