network-request-auditing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process untrusted data from external sources (web pages and API responses) using the
browser_network_requestsandbrowser_console_messagestools. An attacker could embed malicious instructions in network payloads or console logs to influence the agent's behavior. - Ingestion points: Untrusted data enters the agent's context through
browser_network_requestsandbrowser_console_messagescalls as described in SKILL.md. - Boundary markers: The skill does not provide explicit boundary markers or instructions to ignore embedded commands within the network logs.
- Capability inventory: The agent utilizes browser tools including
browser_navigate,browser_snapshot, andbrowser_network_requeststo interact with and observe web environments. - Sanitization: No explicit sanitization or filtering of the external network data is mentioned in the instructions.
Audit Metadata