skill-diff-analyzer

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script located at .agents/skills/platform/skill-lab.mjs to compare two files. This path refers to a platform-internal utility intended for skill management.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes content from external SKILL.md files provided as input.
  • Ingestion points: Two external files, <old>/SKILL.md and <new>/SKILL.md, are read as inputs for comparison.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used during the command-line invocation to handle potentially malicious content within the files.
  • Capability inventory: The skill possesses the ability to execute a platform Node.js script and output a Markdown artifact summarizing the differences.
  • Sanitization: No explicit validation or sanitization is performed on the content of the target files within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:00 AM
Security Audit — agent-trust-hub — skill-diff-analyzer