Skills
Navigate
skills/nanmicoder/dsh-agent-teams/plugin-runtime-debug/Gen Agent Trust Hub

plugin-runtime-debug

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and analyze host API source code from paths like ~/.dsh/source/current. This ingestion of external data constitutes an indirect prompt injection surface.
  • [INDIRECT_PROMPT_INJECTION]: Ingestion points: SKILL.md instructs the agent to open the implementing package in the DSH source checkout and read the actual methods. Boundary markers: Absent. Capability inventory: Diagnostic analysis of logic and state mapping. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 06:18 AM