web-cors
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill provides instructions on how to exfiltrate sensitive data, such as API keys and Personally Identifiable Information (PII), to an external attacker-controlled domain (e.g., https://evil.com).
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves retrieving and analyzing responses from external, potentially untrusted web endpoints, which creates a surface for indirect prompt injection.
- Ingestion points: Responses from targeted web endpoints during probing and exploitation steps.
- Boundary markers: No delimiters or specific instructions are provided to the agent to prevent it from following commands embedded within the retrieved cross-origin data.
- Capability inventory: The skill utilizes network-capable tools (curl, fetch) to access external data and send it to an external server.
- Sanitization: There is no evidence of content sanitization or validation of the data received from external sources before it is processed by the agent.
Audit Metadata