alterlab-pubmed
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bash(python:*)tool to execute a local utility script,scripts/query_pubmed.py, which manages interactions with the PubMed API. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the external PubMed API, which the agent then processes, creating a theoretical injection surface.
- Ingestion points: Literature citations, abstracts, and metadata are retrieved from the NCBI E-utilities API via the
scripts/query_pubmed.pyscript. - Boundary markers: The instructions do not specify any delimiters or safety markers to help the agent distinguish between literature content and its own instructions.
- Capability inventory: The skill is configured to use
Bashfor local script execution andWebFetchfor network operations targeting thencbi.nlm.nih.govdomain. - Sanitization: The Python script uses
urllib.parse.urlencodefor parameter serialization andjson.loadsfor response parsing, providing standard handling for the API communication.
Audit Metadata