xmake-debug-package-source

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of standard development tools and CLI commands including xmake, cmake, curl, tar, git, and diff to facilitate the build and debug process.
  • [EXTERNAL_DOWNLOADS]: The skill provides examples of fetching source code archives from well-known project domains such as zlib.net using curl.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves processing external source code and patch files, which represents a potential attack surface for indirect instructions.
  • Ingestion points: Loading local source directories via the -d flag and applying external patch files using add_patches in SKILL.md.
  • Boundary markers: No specific boundary markers or "ignore instructions" directives are specified for the ingested source data within the skill's instructions.
  • Capability inventory: The skill utilizes build system capabilities including file system access (writing patches), remote synchronization (xmake service), and command execution for compilation (os.vrunv, cmake).
  • Sanitization: Absent; the skill relies on the standard security model of the xmake build system and does not specify additional sanitization for ingested source content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 12:39 PM
Security Audit — agent-trust-hub — xmake-debug-package-source