outline-coach
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a standard assistive persona prompt for creative writing support. No malicious patterns were identified across any threat category.
- [COMMAND_EXECUTION]: There is no evidence of shell commands, subprocess spawning, or script execution.
- [DATA_EXFILTRATION]: The skill does not perform network requests. It stores session progress and structural diagnoses in local files (e.g.,
{project}-outline-coaching-{date}.md) as a persistence mechanism for the user's workflow. - [PROMPT_INJECTION]: The skill uses detailed behavioral constraints to enforce a coaching persona. These instructions are focused on the pedagogical goal of helping the writer discover their own structure rather than attempting to override model safety guidelines.
Audit Metadata