literature-review
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script
scripts/lit_search.pyperforms network requests to well-known and trusted academic services, including Semantic Scholar (api.semanticscholar.org), OpenAlex (api.openalex.org), Crossref (api.crossref.org), and PubMed (eutils.ncbi.nlm.nih.gov). These operations are primary skill functions and target official API endpoints. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection due to its handling of untrusted external data.
- Ingestion points: Data is fetched from external academic APIs in
scripts/lit_search.py, including titles, abstracts, and author names. - Boundary markers: The skill instructions do not implement delimiters or explicit instructions to the agent to disregard potential prompts embedded within the academic content.
- Capability inventory: The skill includes network access to specific academic domains via the
requestslibrary. It does not possess file-writing, privilege escalation, or subprocess execution capabilities. - Sanitization: There is no sanitization or escaping of the fetched text before it is returned to the agent context.
Audit Metadata