focus-coach

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of natural language instructions and YAML configuration. No scripts, binaries, or executable code are included.
  • [SAFE]: The instructions focus on logical coaching frameworks (e.g., bottleneck diagnosis, execution review) and do not contain any patterns associated with prompt injection, data exfiltration, or obfuscation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied information regarding goals and progress. While it lacks explicit boundary markers for this data, it possesses no dangerous capabilities such as file system access or network communication, making the surface for exploitation negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 04:26 AM
Security Audit — agent-trust-hub — focus-coach