fetch-pubmed-recent
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content in the form of abstracts and metadata fetched from external PubMed articles.\n
- Ingestion points: Data is retrieved from the external NCBI E-utilities API or an MCP server during the search and fetch process in Step 4.\n
- Boundary markers: The instructions do not define delimiters or specific warnings to prevent the agent from being influenced by instructions that might be embedded within the external abstracts.\n
- Capability inventory: The skill is instructed to write raw search results and metadata to a local cache file on the filesystem in Step 6.\n
- Sanitization: There are no specified procedures for sanitizing or validating the fetched text before it is returned to the agent context.\n- [EXTERNAL_DOWNLOADS]: The skill performs network operations to retrieve scientific data from a well-known service.\n
- Accesses
eutils.ncbi.nlm.nih.govto fetch search results, summaries, and full abstracts for the agent's research tasks.
Audit Metadata