rev-struct
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates on local project files within a 'decompile' directory provided by the user. Its primary function is pattern matching and data aggregation from C source code to assist in reverse engineering.
- [EXTERNAL_DOWNLOADS]: The skill documentation includes a link to the author's GitHub repository (github.com/P4nda0s/IDA-NO-MCP) to facilitate the manual download of a required IDA Pro plugin. This is documented as a manual step for the user and represents a legitimate vendor resource providing the necessary input data for the skill.
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by processing untrusted external content (decompiled source code).
- Ingestion points: Decompiled C files in the 'decompile/' directory, along with strings.txt, imports.txt, and exports.txt.
- Boundary markers: None identified; the instructions do not specify the use of delimiters or 'ignore' instructions to isolate untrusted content during analysis.
- Capability inventory: The skill's capabilities are limited to reading local files; it does not instruct the agent to execute shell commands, perform network operations, or modify system configurations based on the analyzed content.
- Sanitization: No explicit sanitization or filtering of the source code content is described in the skill workflow.
Audit Metadata