audit
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches audit checklists and methodology from the author's own GitHub repository (
austintgriffith/evm-audit-skills). These resources are used to guide the parallel sub-agents during the audit process. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external smart contract source code from GitHub, which serves as an ingestion point for untrusted data. A malicious contract could potentially contain instructions designed to influence the auditor's findings.
- Ingestion points: External smart contract files (
SKILL.md). - Boundary markers: Not specified.
- Capability inventory: Network access for resource fetching and GitHub issue filing; local file writing for reports.
- Sanitization: Not specified.
Audit Metadata