dwarf-expert
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes binary files, which creates a potential surface for indirect prompt injection via malicious DWARF metadata.
- Ingestion points: Processes DWARF debug information from user-provided binaries (SKILL.md).
- Capability inventory: Uses the Bash tool to execute analysis utilities like llvm-dwarfdump and readelf.
- Sanitization: Includes explicit instructions to treat binaries as untrusted, use patched tools, and operate in isolated environments.
- Boundary markers: No specific LLM boundary markers defined for the tool outputs.
Audit Metadata