coaching-engine

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill. The instructions define interaction guidelines and session persistence mechanisms.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to retrieve information from external sources like documents, codebases, and git records, which presents a surface for indirect prompt injection. However, the skill explicitly mandates that all drafted content must be confirmed by the user, providing a significant mitigation.
  • Ingestion points: Documents, code repositories, and git logs (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Reading local file and git data; writing conclusions to a draft file (SKILL.md).
  • Sanitization: Not explicitly mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 06:53 PM
Security Audit — agent-trust-hub — coaching-engine