academic-guide
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches data from well-known academic sources including Google Scholar, arXiv, ProQuest, and CNKI. These are reputable services and the operations are standard for academic research.
- [PROMPT_INJECTION]: The citation verification workflow creates an attack surface for indirect prompt injection.
- Ingestion points: Data is ingested from external URLs via
webfetchas specified inrules/citation-verification.md. - Boundary markers: There are no explicit delimiters to separate external content from internal instructions.
- Capability inventory: The skill has capabilities for network access and file writing to
/tmp. - Sanitization: There is no explicit sanitization of the content retrieved from external sites.
Audit Metadata