story-coach
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided writing drafts, which serves as a potential entry point for untrusted data. However, the risk is negligible as the skill possesses no network exfiltration capabilities, no shell execution tools, and strictly limits its output to instructional questions and coaching diagnostics.
- [SAFE]: The skill defines robust behavioral constraints that prohibit the generation of story content, which acts as an inherent safety guardrail against generating unsolicited or restricted content.
- [SAFE]: File operations are limited to project-relative paths for session persistence (e.g.,
.story-coach-output.mdand specific session files). The skill follows a transparent process by checking for existing configurations and requesting user consent before establishing new output locations.
Audit Metadata