agent-workbench
Warn
Audited by Snyk on Nov 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to inspect Agent MCP resources and read canonical instructions, which ingest remote server-provided documentation and project task data.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill references an external MCP server endpoint (
https://agent-mcp.devkimson.kro.kr/mcp) owned by an arbitrary personal domain (devkimson.kro.kr), which constitutes a weak/unknown/suspicious operational runtime dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata