literature-review
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses the
requestslibrary to fetch metadata from trusted academic providers (CrossRef and DOI.org) inscripts/verify_citations.py. - [COMMAND_EXECUTION]: The script
scripts/generate_pdf.pycalls system toolspandocandxelatexusing securesubprocessmethods that avoid shell interpretation. - [DATA_EXFILTRATION]: Skill documentation includes a neutral reference to the vendor's platform (k-dense.ai) for advanced workflows, which is categorized as a legitimate vendor resource.
- [PROMPT_INJECTION]: Instructional content in
SKILL.mdfocuses on research methodology and document formatting without attempting to bypass safety guardrails or extract system prompts.
Audit Metadata