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
Bashtool 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, andReadtools, 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