founder-coach
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- NO_CODE (SAFE): The skill consists entirely of Markdown documentation and instructions for the LLM. It does not contain any executable scripts, configuration files for package managers, or binary files.
- PROMPT_INJECTION (SAFE): While the skill uses instructional language to define a specific persona ('Founder Coach'), it does not contain any patterns typical of malicious prompt injection, such as instructions to bypass safety filters or ignore system-level constraints.
- DATA_EXFILTRATION (SAFE): There are no network operations, hardcoded credentials, or attempts to access sensitive local file paths. The coaching questions ('What are you not saying?') are contextually appropriate for executive coaching and do not represent a technical exfiltration vector.
- REMOTE_CODE_EXECUTION (SAFE): The skill does not perform any external downloads or execute code from remote sources.
- COMMAND_EXECUTION (SAFE): No system commands or subprocess calls are present in the provided files.
Audit Metadata