easysdd-feature
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a structural router for a multi-stage development workflow. It does not perform network operations, execute arbitrary shell commands, or handle sensitive credentials.
- [DATA_EXPOSURE]: The skill instructs the agent to read file names and content from the
easysdd/features/directory to determine state. This is a standard operational requirement for managing project documentation and does not constitute unauthorized data exposure. - [PROMPT_INJECTION]: While the skill reads untrusted data (local feature design and brainstorm files), this represents a standard indirect prompt injection surface. The risk is minimized as this skill only performs routing logic and does not execute the content of those files as code.
- Ingestion points: Markdown and YAML files within
easysdd/features/. - Boundary markers: Not explicitly defined in this router file.
- Capability inventory: Only performs directory globbing and status checking.
- Sanitization: None observed, but not applicable to the routing logic.
Audit Metadata