skills/smallnest/goal-workflow/graph/Gen Agent Trust Hub

graph

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The progress dashboard generated by the skill loads the Mermaid.js library from the well-known jsDelivr CDN to render visual task dependency graphs. This is a neutral finding and follows standard development practices for dashboarding.
  • [PROMPT_INJECTION]: The skill ingests external data (such as PRDs, SPEC files, and issue descriptions) and interpolates this content into prompts for subagents, creating an indirect prompt injection surface.
  • Ingestion points: Task descriptions, PRD/SPEC files, and GitHub issue bodies processed during the decomposition phase.
  • Boundary markers: The prompt template defined for subagents lacks explicit delimiters or instructions to ignore potential commands embedded within the interpolated task data.
  • Capability inventory: The skill and its subagents possess capabilities for file system modification, git repository management, and pull request creation.
  • Sanitization: The skill does not perform specific validation or sanitization of the input text before passing it to subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 09:16 AM
Security Audit — agent-trust-hub — graph