offensive-vuln-classes
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for analyzing external files such as source code, binaries, and configurations, which creates an inherent attack surface for indirect prompt injection if the analyzed files contain malicious instructions.\n
- Ingestion points: Source code, binary artifacts, and configuration files identified during the 'Surface & Architecture Inventory' phase (SKILL.md).\n
- Boundary markers: No explicit delimiters or 'ignore' instructions for external content are specified in the operational workflow.\n
- Capability inventory: The skill references the use of search tools (rg), AST analysis, binary disassembly tools, and the execution of test suites (npm test).\n
- Sanitization: No sanitization, validation, or filtering of the content being analyzed is described in the provided instructions.
Audit Metadata