token-risk-scanner
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external blockchain sources (token names, symbols, and contract attributes) retrieved via the GoPlus API. This metadata is interpolated into security reports, creating a surface where maliciously crafted contract information could attempt to influence the agent's summary or recommendations.
- Ingestion points:
scripts/goplus-token-check.pyand MCP tools (goplus_token_security, etc.) retrieve data from external API endpoints. - Boundary markers: The skill instructions do not explicitly define delimiters or provide specific instructions for the agent to isolate external strings when generating the report.
- Capability inventory: The skill is granted access to GoPlus security tools and file system tools (
Read,Grep,Glob). - Sanitization: No sanitization or escaping of retrieved token metadata is performed before it is interpolated into the final markdown report template.
Audit Metadata