Skills
skills/yonatangross/orchestkit/commit/Gen Agent Trust Hub

commit

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses local git and validation tools without network access or credential exposure.
  • [PROMPT_INJECTION]: The skill ingests data from local agent activity logs for attribution. Ingestion points: .claude/agents/activity/{branch}.jsonl (Phase 3b). Boundary markers: Absent. Capability inventory: Bash tool (git commit). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 02:03 AM