site-content-catalog
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script downloads sitemaps, RSS feeds, and webpage content from user-specified domains using the
requestslibrary. This is the core functionality of the content cataloging tool. - [DATA_EXFILTRATION]: When the optional Apify fallback is used, the script transmits the
GOOSEWORKS_API_KEYtoapp.gooseworks.ai. This is standard functionality for the vendor's own infrastructure and proxy services. - [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data (such as page titles and metadata) from external websites and including them in the final reports.
- Ingestion points:
scripts/catalog_content.pyfetches data from external URLs provided by the user. - Boundary markers: The generated reports do not use explicit delimiters or warnings to separate external content from the agent's instructions.
- Capability inventory: The script has permissions to perform network requests and write data to local files.
- Sanitization: The script removes HTML tags but does not sanitize the text content for potential prompt injection strings that could influence an agent reading the output.
Audit Metadata