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
Risk Level
SAFE
Analyzed
Apr 22, 2026, 12:32 AM