ai-writing-quality-check
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-provided text in the
contentparameter, which is a surface for indirect prompt injection. - Ingestion points: The
contentparameter within thecheck_for_banned_phrasesaction inSKILL.md. - Boundary markers: There are no specific delimiters or instructions to ignore embedded commands within the processed content.
- Capability inventory: The skill is designed for iterative rewrite loops where the agent modifies text based on tool output. It does not request local code execution or file system access.
- Sanitization: No sanitization or escaping of the input content is specified in the skill files.
- [EXTERNAL_DOWNLOADS]: The documentation provides installation commands for required setup skills. These resources are hosted in the author's official GitHub repository (
AgentPMT/agent-skills) and are standard for this product's ecosystem.
Audit Metadata