fetching-blocked-urls
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell-based
curlcommands in a retry loop to interact with an external service.- [EXTERNAL_DOWNLOADS]: Fetches markdown-formatted web content from the Jina AI reader service (r.jina.ai) when standard fetch tools fail.- [PROMPT_INJECTION]: Creates an attack surface for indirect prompt injection from malicious instructions embedded in the fetched external web content. - Ingestion points: Markdown content retrieved via
curlfrom r.jina.ai in SKILL.md. - Boundary markers: Absent; the fetched content is returned directly to the agent's context without delimiters or safety framing.
- Capability inventory: Shell execution capabilities (
curl) and native web tools. - Sanitization: No sanitization or content validation is performed on the data returned by the third-party service.
Audit Metadata