article-page-generator
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted external sources, which could contain instructions designed to influence the agent's behavior during analysis.
- Ingestion points: Processes content from external competitor URLs and web search results during the 'Research Phase' (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the fetched external content.
- Capability inventory: The agent generates article structures, SEO metadata, and JSON-LD schema based on the ingested content.
- Sanitization: No explicit sanitization or filtering of the external source data is performed before processing.
Audit Metadata