NYC
skills/getsentry/warden/agent-prompt/Gen Agent Trust Hub

agent-prompt

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • SAFE (SAFE): No malicious patterns detected. The skill consists entirely of Markdown documentation files.
  • NO_CODE (SAFE): The skill contains no executable scripts (Python, JavaScript, etc.) or binary files. It only utilizes the 'Read', 'Grep', and 'Glob' tools which are standard for documentation retrieval.
  • EXTERNAL_DOWNLOADS (SAFE): Documentation includes links to reputable external sources (Anthropic, OpenAI, Vercel) for educational purposes, but no code is downloaded or executed from these sources.
  • PROMPT_INJECTION (SAFE): While the skill contains advice on how to write prompts, it does not include instructions designed to bypass safety filters or override agent constraints for malicious purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:28 PM