find-oep
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted binary data from external PE files and memory, creating an attack surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through
mcp__x64dbg__read_memory,mcp__x64dbg__disassemble, and symbol lookups from the target binary. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings when interpreting data read from debuggee memory.
- Capability inventory: The agent has access to powerful tools including memory modification (
mcp__x64dbg__write_memory), arbitrary debugger command execution (mcp__x64dbg__execute_command), and local file writing (Write). - Sanitization: There is no mention of sanitizing or escaping the content retrieved from the target process before the agent analyzes it, which could allow maliciously crafted strings in the binary to influence agent behavior.
Audit Metadata