offensive-iot
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code, binaries, and configuration files, posing a risk of indirect prompt injection.\n
- Ingestion points: Target source code and firmware binaries described in the operational workflow (SKILL.md).\n
- Boundary markers: The instructions do not define delimiters or specific safety warnings for processing embedded instructions within analyzed data.\n
- Capability inventory: Search (rg) and binary disassembly tools mentioned in the integration section, and command execution (npm test) mentioned in the checklist (SKILL.md).\n
- Sanitization: No sanitization or escaping protocols are specified for handling potentially malicious content in the input files.\n- [NO_CODE]: The skill consists solely of markdown instructions and YAML configuration. It does not contain or distribute executable scripts or binaries.
Audit Metadata