agency-frontend-developer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define tasks involving the consumption of data from external sources such as backend APIs and WebSocket/RPC bridges for editor integrations.
- Ingestion points: The skill is tasked with integrating with backend APIs and implementing WebSocket/RPC bridges for cross-application communication as described in the 'Editor Integration Engineering' and 'Create Modern Web Applications' sections of SKILL.md.
- Boundary markers: There are no instructions provided for the agent to use delimiters or ignore embedded instructions when processing data from these external streams.
- Capability inventory: The agent is instructed to build application logic, handle event flows, and create editor extension commands which could be influenced by malicious data.
- Sanitization: No specific sanitization or validation logic is defined for the external data ingested through APIs or RPC channels.
Audit Metadata