coverage-check
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its intended function of querying the GDELT Project's public API to provide news coverage analysis. The implementation is transparent and does not involve suspicious activities.
- [EXTERNAL_DOWNLOADS]: The script
scripts/coverage.pyfetches news metadata from the well-known GDELT Project API (api.gdeltproject.org). This is a standard and expected operation for the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data (news headlines and metadata) from the GDELT API.
- Ingestion points: Fetches data from
api.gdeltproject.orginscripts/coverage.py. - Boundary markers: The output is formatted into structured Markdown or JSON, and the documentation explicitly instructs the agent that this data should be used for evidence rather than direct decision-making.
- Capability inventory: The skill has no file-write, subprocess execution, or dangerous network capabilities beyond the API query.
- Sanitization: Titles are normalized and tokenized for clustering, which inherently sanitizes simple text-based injection attempts.
Audit Metadata