literature-review
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted content from external academic APIs which could contain malicious instructions designed to influence agent behavior.
- Ingestion points: The
scripts/lit_search.pyscript fetches paper titles and abstracts from Semantic Scholar, OpenAlex, Crossref, and PubMed. - Boundary markers: The script outputs data as a JSON object but does not include specific boundary markers or 'ignore' instructions to separate data from commands.
- Capability inventory: The script is limited to performing network GET requests and printing to stdout; it does not have the ability to write to the file system or execute arbitrary commands.
- Sanitization: No sanitization or filtering is applied to the abstracts or metadata retrieved from the external services.
Audit Metadata