reverse-eng-go-rust
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted binary files which are potential vectors for indirect prompt injection via embedded strings or metadata such as function names, panic messages, or source paths.\n
- Ingestion points: Untrusted ELF/PE/Mach-O binaries as specified in triage or scope files.\n
- Boundary markers: Absent; the instructions do not specify any delimiters or warnings to ignore embedded strings that might contain natural language instructions.\n
- Capability inventory: The skill utilizes powerful system-level tools including
gdb,frida,IDA, andGhidrato inspect and execute code from untrusted sources.\n - Sanitization: No sanitization or validation of the strings extracted from the binary is mentioned before they are processed or interpreted by the agent.\n- [EXTERNAL_DOWNLOADS]: The documentation references and adapts content from an external, non-trusted GitHub repository (
github.com/zhaoxuya520/reverse-skill).
Audit Metadata