always-on-guidance

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • [No Code] (SAFE): The analysis confirms the skill contains only Markdown-based instructions and metadata. No scripts (.py, .js, .sh), binaries, or configuration files for package managers were found.
  • [Prompt Injection] (SAFE): Instructions provided are for operational alignment (tool usage and output formatting) and do not attempt to bypass safety guardrails or override system instructions for malicious purposes.
  • [Data Exfiltration] (SAFE): There is no code present to perform network requests or access sensitive local files. Mentions of git-backed persistence relate to the intended functionality of external tools, not the skill's own implementation.
  • [External Downloads] (SAFE): No remote URLs or third-party package dependencies are referenced for download or execution.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:17 AM