literature-review

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local utility scripts such as scripts/scholar_search.py and scripts/pdf_parser.py. These scripts are used for their intended purpose of searching academic databases and extracting information from research papers.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates data retrieval from well-known and reputable academic services including CrossRef, PubMed, Semantic Scholar, and arXiv. These connections are used to fetch metadata and publication details for literature review purposes.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and process data from external web sources and user-provided PDF files. This is inherent to its primary function of literature analysis.
  • Ingestion points: External data enters the agent context through web search results and the output of the PDF parsing script (scripts/pdf_parser.py).
  • Boundary markers: The skill does not explicitly define delimiters or instructions to ignore potential commands embedded within the processed literature.
  • Capability inventory: Across its instruction set, the agent possesses Bash for script execution, WebSearch/WebFetch for networking, and Write/Edit for file manipulation.
  • Sanitization: There are no specific sanitization or validation routines described for the content extracted from external scholarly sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:57 AM
Security Audit — agent-trust-hub — literature-review