skills/schpet/toolbox/changelog/Gen Agent Trust Hub

changelog

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No attempts to bypass safety filters or override system instructions were detected.
  • [Data Exposure & Exfiltration] (SAFE): The skill only interacts with local project files (CHANGELOG.md) and git history for its intended purpose. No sensitive data exfiltration or hardcoded credentials found.
  • [Remote Code Execution] (SAFE): There are no commands to download or execute remote scripts.
  • [Command Execution] (SAFE): The command usage is restricted to the 'changelog' CLI for document maintenance, which aligns with the skill's primary purpose.
  • [Indirect Prompt Injection] (SAFE): While the skill can process git commits (untrusted data) via 'changelog review', this is a standard feature for changelog management. Ingestion points: git history; Boundary markers: absent; Capability inventory: changelog CLI commands; Sanitization: user/agent review in editor. Risk is negligible and tied to primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM