finish-release

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it executes commands derived from local repository data.\n
  • Ingestion points: Phase 2 reads test commands from package.json and Makefile.\n
  • Boundary markers: None present; the agent is not instructed to ignore malicious instructions within these files.\n
  • Capability inventory: Uses Bash to execute the identified scripts and manage the release via git and gh.\n
  • Sanitization: No validation is performed on the commands retrieved from configuration files before they are passed to the shell.\n- [COMMAND_EXECUTION]: The skill performs significant repository operations including branch merging, tagging, and pushing using git. It also creates external releases using the gh tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 10:24 AM