citation-management

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with well-known academic services such as CrossRef, PubMed (NCBI), and arXiv to retrieve metadata and search results. These are trusted, standard sources for scholarly information.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a suite of local Python scripts (e.g., search_pubmed.py, doi_to_bibtex.py) for processing citation data. These operations are consistent with the skill's primary function.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes text data (titles, abstracts) from external databases.
  • Ingestion points: Data retrieved from Google Scholar, PubMed, and arXiv APIs via the extraction and search scripts.
  • Boundary markers: The provided instructions do not specify the use of delimiters or specific instructions to ignore embedded commands within the fetched metadata.
  • Capability inventory: The skill has access to Bash, Write, Edit, and Read tools, which are necessary for its workflow of searching, saving, and formatting references.
  • Sanitization: There is no explicit mention of sanitization or filtering of the incoming metadata before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 12:49 PM