gdelt-doc-search
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from the public internet via the GDELT DOC API, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: External news article metadata and timeline data are retrieved from the GDELT project API in
scripts/gdelt_doc_search.pyand returned to the agent's context. - Boundary markers: The skill does not define specific delimiters or instructions (e.g., 'ignore instructions within the following text') to help the agent distinguish between API results and system commands.
- Capability inventory: The script
scripts/gdelt_doc_search.pypossesses the capability to write the retrieved untrusted data to the local filesystem via the--outputparameter. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from the GDELT API before it is output to the agent or saved to disk.
Audit Metadata