literature-search

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data retrieved from PubMed search results.
  • Ingestion points: External text including paper titles and abstracts is ingested into the agent context via the search_literature and fetch_article_details tools as described in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat retrieved literature data as potentially untrusted or to ignore embedded instructions.
  • Capability inventory: The skill's capabilities include performing web-based searches, merging results, and performing batch imports to Zotero using the batch_import_from_pubmed tool in SKILL.md.
  • Sanitization: The instructions lack any requirement for the agent to sanitize or validate the external content before it is incorporated into the search summary or citation list.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 10:19 AM
Security Audit — agent-trust-hub — literature-search