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.py script.
  • 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 Bash for local script execution and WebFetch for network operations targeting the ncbi.nlm.nih.gov domain.
  • Sanitization: The Python script uses urllib.parse.urlencode for parameter serialization and json.loads for response parsing, providing standard handling for the API communication.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:36 PM