proofread-grammar

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its interaction with untrusted document content.
  • Ingestion points: The skill ingests data from Application.Selection in SKILL.md.
  • Boundary markers: No specific delimiters or instructions are present to ensure the agent disregards malicious commands embedded within the text to be proofread.
  • Capability inventory: The skill can modify the user's document content by overwriting selections.
  • Sanitization: There is no evidence of input sanitization or filtering to prevent the agent from executing instructions contained within the document text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 04:55 PM
Security Audit — agent-trust-hub — proofread-grammar