cw-sorkin

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text for analysis, which represents a surface for indirect prompt injection attacks where instructions could be embedded in the data.
  • Ingestion points: User input is ingested via the /cw-sorkin command or workspace text selection as defined in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or boundary markers (e.g., triple quotes or XML tags) to isolate the user-provided text from the agent's logic.
  • Capability inventory: The skill contains no executable scripts, subprocess calls, file system operations, or network requests, which significantly mitigates the risk of an injection attack.
  • Sanitization: No explicit sanitization, filtering, or validation of the ingested text is defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:43 PM
Security Audit — agent-trust-hub — cw-sorkin