vike-web-research
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests untrusted data from external websites.
- Ingestion points: Content retrieved from external URLs via the
vike web fetchcommand. - Boundary markers: None specified within the playbook instructions.
- Capability inventory: The workflow is limited to using the
vike web searchandvike web fetchtools. - Sanitization: The skill does not define specific sanitization logic, relying on the underlying agent platform's handling of tool outputs.
Audit Metadata