request-interceptor-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes functionality for processing external data sources, specifically webhooks and third-party APIs, which presents a surface for indirect prompt injection.
- Ingestion points: The skill activates when users request assistance with webhooks and API integration patterns, implying the processing of external data structures.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within the external data (e.g., within a webhook payload or API documentation).
- Capability inventory: The skill is granted powerful capabilities including
Bash(cmd:*),Write, andEdit, which increases the potential impact if a successful injection occurs. - Sanitization: The instructions do not specify any validation or sanitization steps for the data received from external integrations before incorporating it into code generation or system commands.
Audit Metadata