cross-gcc

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands for toolchain installation, source code compilation, and running binaries via QEMU emulation.
  • [PRIVILEGE_ESCALATION]: Includes instructions for using sudo to install packages via apt, which is required for setting up the necessary development environment.
  • [EXTERNAL_DOWNLOADS]: Mentions the use of debootstrap and downloading sysroots from official sources like Raspbian repositories for cross-compilation.
  • [INDIRECT_PROMPT_INJECTION]: The skill interprets user queries to provide build instructions, creating a surface for potential injection if user input is directly used in shell commands.
  • Ingestion points: User queries about target architectures and file paths in SKILL.md.
  • Boundary markers: No specific delimiters used to separate user-provided data.
  • Capability inventory: Shell execution capabilities for compilers, build tools, and emulators.
  • Sanitization: No input sanitization or escaping is documented for the generated commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:29 PM