web3-start-here
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a master index and curriculum for smart contract security research. It contains no scripts, network operations, or access to sensitive local environment data.\n- [INDIRECT_PROMPT_INJECTION]: The skill structure involves the sequential reading of multiple markdown files, which represents a surface for indirect prompt injection.\n
- Ingestion points: SKILL.md (references files 00 to 36).\n
- Boundary markers: Absent.\n
- Capability inventory: No tool invocations, subprocess calls, or network operations are present in this file.\n
- Sanitization: Absent.\n
- The lack of exploitable capabilities within this file mitigates the risk posed by the data ingestion surface.
Audit Metadata