help-center-article-generator
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data sources including support ticket exports (CSV/lists), internal feature documentation, and external help articles via URLs.
- Ingestion points: Support ticket exports, PRD/spec files, and external article URLs provided during the intake phase in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or "ignore embedded instructions" warnings when processing these external inputs.
- Capability inventory: The skill performs file system writes to save generated articles to
clients/<client-name>/customer-success/help-center/as described in SKILL.md. - Sanitization: No explicit sanitization, filtering, or validation of the input content is mentioned before the reasoning process or file output occurs.
Audit Metadata