skills/dslsdzc/rev-skills/re-cpp-abi/Gen Agent Trust Hub

re-cpp-abi

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to install and use standard system utilities for binary analysis.
  • Package installation: Provides commands for apt, dnf, pacman, and brew to install binutils and llvm packages.
  • Local tool execution: Includes shell commands for readelf, strings, llvm-objdump, llvm-readobj, and c++filt to inspect local binary files (e.g., sample).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external binary files, which serves as an ingestion point for potentially adversarial data contained within the file's strings or metadata.
  • Ingestion points: Binary data extracted via strings, readelf, and llvm-readobj is intended for agent processing in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded in the binary data.
  • Capability inventory: The skill focuses on analysis and information recovery; it does not include instructions for file-write operations, network requests, or privilege escalation based on the analyzed data.
  • Sanitization: No explicit sanitization or filtering of the binary tool output is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:04 AM