skills/howells/skills/foreman/Gen Agent Trust Hub

foreman

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The analyzed files contain only natural language instructions and YAML configuration for agent orchestration. No executable scripts, network requests, or sensitive file accesses are present.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow involving the ingestion of reports from subagents (Ingestion points: SKILL.md Dispatch and Inspect steps). The Foreman role possesses capabilities to review diffs and coordinate other agents. The instructions provide a mitigation by directing the agent to prioritize inspection of 'git diff' output over natural language summaries from subagents (Sanitization: 'Inspect the diff, not the report').
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 10:12 AM