generating-faqs-and-help-content

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill does not contain any malicious code, external dependencies, or commands.
  • [NO_CODE]: This skill is entirely markdown-based, providing instructions and templates for the AI agent without any accompanying scripts or executables.
  • [PROMPT_INJECTION]: No evidence of jailbreaking, system prompt extraction, or safety override instructions was found.
  • [INDIRECT_PROMPT_INJECTION]: While the skill defines a workflow to ingest external data such as support tickets and chat logs, which is a common surface for indirect injection, the absence of tool use or execution capabilities makes this surface low-risk. 1. Ingestion points: Support tickets, chat logs, social comments, reviews (Step 1). 2. Boundary markers: None present in templates. 3. Capability inventory: No tools or scripts identified. 4. Sanitization: Not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:32 PM