research-check
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed exclusively of natural language instructions and does not contain any executable scripts or binary files.
- [PROMPT_INJECTION]: The skill processes untrusted external articles, which serves as an ingestion point for untrusted data. 1. Ingestion points: Article content provided by the user or fetched from external URLs. 2. Boundary markers: None identified (the instructions do not use delimiters to separate untrusted content from the system prompt). 3. Capability inventory: Uses WebFetch and WebSearch tools to perform external verification. 4. Sanitization: No specific sanitization or filtering of external content is performed. This indirect prompt injection surface is inherent to the primary functionality of a research audit tool and is considered acceptable.
Audit Metadata