skills/ilteoood/harness/thermos/Gen Agent Trust Hub

thermos

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill acts as a coordinator for specialized subagents and contains only natural language instructions. It does not contain scripts, shell commands, or direct network access.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from pull requests and diffs. Ingestion points: Git diffs and file context (SKILL.md). Boundary markers: None explicitly defined. Capability inventory: Launching subagents for code review. Sanitization: None explicitly mentioned. As this is a code review tool, this surface is expected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:02 AM
Security Audit — agent-trust-hub — thermos