backlog-todo
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill provides guidelines for document structure and manual state transitions within a local Markdown file.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled data within the
TODO.mdfile. While this represents a theoretical injection surface, the skill's limited capabilities (moving text blocks within a specific file) and standard document management purpose present no significant risk. - Ingestion points: Reads and parses
TODO.mdfile content. - Boundary markers: None explicitly defined in the templates.
- Capability inventory: Limited to reading, modifying, and moving text blocks within the local project file system.
- Sanitization: No specific sanitization logic is present for user-supplied story content.
Audit Metadata