skills/echovic/boss-skill/boss/Gen Agent Trust Hub

boss

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The orchestrator utilizes a local CLI suite (boss runtime) and the Bash tool to manage development workflows. It implements a safety hook to intercept and block dangerous operations such as rm -rf, git push --force, and DROP TABLE.
  • [EXTERNAL_DOWNLOADS]: The skill manages its own updates via npm update @blade-ai/boss-skill. It also utilizes agent-browser from Vercel Labs, a trusted organization, to perform automated UI testing during the quality assurance phase.
  • [PROMPT_INJECTION]: The skill is an orchestration engine that interpolates user requirements into sub-agent prompts. While this presents a surface for indirect prompt injection, the risk is significantly mitigated by mandatory technical reviews, automated code-quality gates (Gate 0), and an 'attack-oriented' QA protocol defined in the sub-agent instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 05:18 AM
Security Audit — agent-trust-hub — boss