coaching-pms
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is entirely composed of Markdown documentation, templates, and reference guides. No Python scripts, Node.js packages, or shell commands are included.
- [DATA_EXPOSURE] (SAFE): The skill explicitly advises users to use anonymized examples of work and warns against requesting sensitive personal data in the 'SKILL.md' and 'INTAKE.md' files. There are no mechanisms for data exfiltration.
- [PROMPT_INJECTION] (SAFE): No patterns of system prompt extraction, role-play bypass, or instruction-override attempts were detected. The instructions are focused on professional coaching workflows.
- [INDIRECT_PROMPT_INJECTION] (SAFE):
- Ingestion points: Processes user-provided work artifacts (PRDs, roadmaps) as described in
SKILL.md. - Boundary markers: Instructions explicitly request 'anonymized' inputs.
- Capability inventory: Zero technical capabilities; the skill does not use tools to execute code, write files, or access the network.
- Sanitization: Relies on human-in-the-loop anonymization guidelines.
Audit Metadata