rev-struct

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to manually download a plugin from the author's GitHub repository (github.com/P4nda0s/IDA-NO-MCP). This is a legitimate vendor resource used to facilitate data export for the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from decompiled files and string tables, creating a potential attack surface for indirect prompt injection.
  • Ingestion points: Decompiled C files (decompile/*.c), memory dumps (memory/), and metadata files (strings.txt, imports.txt, exports.txt).
  • Boundary markers: The skill does not define specific boundary markers for the ingested content.
  • Capability inventory: The skill's operations are limited to code pattern analysis and generating text-based struct definitions; the instructions do not utilize network access or file-writing capabilities.
  • Sanitization: No specific sanitization or filtering of the processed content is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:39 PM
Security Audit — agent-trust-hub — rev-struct