crossref-lookup
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches citation metadata from the Crossref REST API (api.crossref.org) and utilizes the
requestslibrary, which is a common and well-known dependency managed by theuvtool. - [COMMAND_EXECUTION]: The skill uses a bash wrapper (
scripts/lookup) to execute its core Python functionality, passing user-provided arguments to the script viauv run. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external publication data, creating a potential surface for indirect prompt injection.
- Ingestion points:
scripts/lookup.pyreads user-specified local files for bibliography auditing and fetches publication metadata from the externalapi.crossref.orgendpoint. - Boundary markers: The instructions do not define specific delimiters to separate untrusted citation data from the agent's instructions.
- Capability inventory:
scripts/lookup.pyis capable of making network GET requests to retrieval metadata and writing output to a local file using the--outputparameter. - Sanitization: The tool normalizes DOI strings for lookup but does not implement specific sanitization or filtering for the metadata fields returned by the Crossref API before presenting them to the agent.
Audit Metadata