prompt-improver

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill's core functionality is to act as a linter and optimizer for prompt engineering, which is a benign and productive use case.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted instruction files which could contain hidden commands intended to manipulate the agent.
  • Ingestion points: Target SKILL.md and agent markdown files are read into context.
  • Boundary markers: None identified; the skill processes the entire file content as analysis input.
  • Capability inventory: Tools include Read, Write, Edit, Glob, and Grep.
  • Sanitization: No explicit sanitization or filtering of external content is performed.
  • [EXTERNAL_DOWNLOADS]: The skill references official prompt engineering documentation and guides from Anthropic. These resources are from a well-known, trusted service and do not constitute a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 08:36 PM