capa
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted native binaries and ARM64 ELF samples as part of a triage workflow.
- Ingestion points: Native binaries and ARM64 ELF samples provided for triage (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are provided to separate the content extracted from the binary from the agent's instructions.
- Capability inventory: The skill interacts with other internal tools such as
/ghidraand/verify-security-findingbased on the results of the triage. - Sanitization: There are no explicit instructions to sanitize or escape strings or metadata extracted from the binaries before they are processed or passed to other tools.
Audit Metadata