generating-faqs-and-help-content
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple customer-facing channels to generate support content. 1. Ingestion points: Support tickets, chat logs, sales calls, reviews, social comments, search queries, user surveys, and community forums (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore commands within the source data. 3. Capability inventory: The skill utilizes the agent's content generation and summarization capabilities on these external inputs. 4. Sanitization: No sanitization or validation of the input data is described.
- [SAFE]: The skill provides links to official documentation and guidelines from well-known services including Intercom, Zendesk, and HelpScout.
- [NO_CODE]: The skill consists of markdown templates and instructions with no embedded scripts or executables.
Audit Metadata