devrel-story-craft
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill is entirely composed of instructions, templates, and rules for planning and auditing marketing and product narratives.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted user data for review. 1. Ingestion points: User-provided drafts, posts, and emails are processed in SKILL.md. 2. Boundary markers: Absent; instructions do not define delimiters for user input. 3. Capability inventory: None; no file-write, network operations, or shell commands exist in any scripts or references. 4. Sanitization: Absent; user content is evaluated directly against guidelines.
Audit Metadata