couch-to-goal-runner
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides a framework for generating text-based running plans. It does not include any scripts, command-line executions, or system-level operations.
- [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass AI safety filters, extract system prompts, or override agent behavior. The language is consistent with its stated purpose of providing fitness guidance.
- [DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or accesses to sensitive file paths. The skill operates entirely within the conversation context.
- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts, install packages, or use dynamic execution functions like eval or exec.
- [SAFE]: The skill includes a clear safety disclaimer advising users to consult a doctor if they have health conditions, which is a best practice for fitness-related instructions.
Audit Metadata