scrape
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the internet, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The
scripts/scrape.shscript fetches data from user-provided URLs using the Bright Data Web Unlocker API. - Boundary markers: There are no specific delimiters or warnings used to separate the external data from the agent's internal instructions.
- Capability inventory: The skill's capabilities are focused on network requests via
curland data processing withjq. - Sanitization: The fetched content is returned as raw markdown without sanitization or filtering of potential malicious instructions.
Audit Metadata