offensive-container-escape
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 untrusted external data, including source code, binaries, and configuration files, creating a surface for indirect prompt injection. * Ingestion points: Processes configuration files, source code, and binary metadata during discovery and verification phases (SKILL.md). * Boundary markers: The instructions do not specify explicit delimiters or warnings for the agent to ignore instructions inside analyzed data. * Capability inventory: Uses search tools (rg), AST analysis, and binary disassembly. * Sanitization: No explicit sanitization or validation of external content is mentioned.
Audit Metadata