skills/broomva/skills/prompt-library/Gen Agent Trust Hub

prompt-library

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches prompt data from the vendor's official API at https://broomva.tech/api/prompts. This is standard functionality for the skill's purpose.
  • [PROMPT_INJECTION]: The skill ingests instructions from an external repository to influence agent behavior. \n
  • Ingestion points: scripts/prompt-sync.py via the pull command. \n
  • Boundary markers: None; the content is provided directly to the agent context. \n
  • Capability inventory: The agent is instructed to use the pulled content for system-level tasks (e.g., code review, research). \n
  • Sanitization: None; the skill assumes the source repository is trusted.
  • [COMMAND_EXECUTION]: Executes a local Python script (scripts/prompt-sync.py) to manage API requests. The script uses built-in modules for network communication and does not perform unsafe shell execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 03:33 PM
Security Audit — agent-trust-hub — prompt-library