offensive-wpa3-sae
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external wireless configuration files, source code, and binaries. This creates a surface for indirect prompt injection if the audited materials contain malicious instructions designed to influence the agent. * Ingestion points: The operational workflow in SKILL.md specifies identifying entrypoints, trust boundaries, parsers, and configuration files for inspection. * Boundary markers: There are no explicit instructions or delimiters defined to isolate the agent's logic from instructions that might be embedded in the audited data. * Capability inventory: The skill utilizes analysis tools including rg (ripgrep), AST analysis, and decompilation to process target data. * Sanitization: No specific input sanitization or instruction-filtering mechanisms are described for handling external data.
Audit Metadata