Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/windsurf-cascade-context/Gen Agent Trust Hub

windsurf-cascade-context

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests arbitrary project data to map codebase structure and maintain documentation. 1. Ingestion points: Instructions in references/implementation.md describe reading and documenting project files like api-surface.md and project-overview.md. 2. Boundary markers: No delimiters or protective instructions are specified to prevent the agent from obeying commands embedded in project documentation. 3. Capability inventory: The skill is configured to use Read, Write, Edit, Grep, and Glob tools for file management. 4. Sanitization: The skill does not implement validation or sanitization for the project content it processes.
  • [NO_CODE]: The skill consists exclusively of Markdown documentation files providing workflow guidance and does not include any Python, JavaScript, shell scripts, or other executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:49 AM
Security Audit — agent-trust-hub — windsurf-cascade-context