antinet-security-scan
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a security gateway that ingests and processes untrusted data from external files and URLs, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The
targetparameter inSKILL.mdaccepts local file paths (PDF, Word, etc.) and external URLs for scanning. - Boundary markers: The skill is designed to output a structured
verdictand scanning report, providing a clear boundary between the raw data and the agent's decision-making process. - Capability inventory: The skill performs file type detection using
python-magicand validates domains against a local blacklist. - Sanitization: The skill itself serves as a sanitization layer, employing a 'zero-trust' policy where identification failures or library errors result in immediate rejection of the input.
Audit Metadata