grammar-checker

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text that could contain malicious instructions designed to manipulate the agent.
  • Ingestion points: Analyzes text provided by users or read from the file system using the Read tool as described in SKILL.md.
  • Boundary markers: The skill's instructions do not implement delimiters or 'ignore' directives to separate user input from system prompts.
  • Capability inventory: The agent is granted access to Read, Write, Edit, Grep, Glob, and AskUserQuestion tools, which could be leveraged if an injection attack succeeds.
  • Sanitization: There are no verification steps or sanitization rules for the processed content to prevent instruction override.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:26 AM
Security Audit — agent-trust-hub — grammar-checker