scv-scan
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it instructs the agent to read and analyze untrusted external Solidity files.
- Ingestion points: The agent is directed to read external Solidity codebase files (
path/to/file.sol) during Phase 2 (Codebase Sweep) and Phase 3 (Deep Validation). - Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from obeying instructions that might be maliciously embedded within Solidity code comments or strings.
- Capability inventory: The skill is granted access to high-privilege tools such as
Bash,Write, andTask, which could be exploited if an attacker successfully influences the agent's behavior via injected code. - Sanitization: There is no evidence of pre-processing or sanitization steps to filter out natural language instructions from the Solidity source code before analysis.
Audit Metadata