nasa-image-to-atlas-page
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it is designed to fetch and process content from external websites.
- Ingestion points: External NASA/ESA image URLs and source page content ingested via the
imageinput andWebFetchtool. - Boundary markers: The workflow instructions define specific data to extract (catalog IDs, facts), but they do not provide explicit delimiters or instructions to ignore potential commands embedded within the external source text.
- Capability inventory: The skill uses
WebFetchfor network access andWritefor local file system modification across thecontent/atlas/**directory. - Sanitization: No explicit sanitization or escaping of external content is defined before it is formatted into the MDX output.
- [EXTERNAL_DOWNLOADS]: The skill uses the
WebFetchtool to retrieve data from external domains. While the intended use case involves trusted scientific sources, the skill can process any URL provided to theimageparameter.
Audit Metadata