lindy-observability
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an observability workflow that processes data from external task events, creating a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via the
Agent Task Changetrigger and theGet Task Detailstool as described inSKILL.mdandimplementation-guide.md. - Boundary markers: The instructions provide clear boundaries, explicitly requiring the exclusion of task inputs, outputs, customer content, and secrets from telemetry.
- Capability inventory: The agent is instructed to use the
HTTP Requestaction to send data to an external receiver. - Sanitization: The skill provides a TypeScript implementation that strictly validates the schema, limits request body size, and enforces an allowlist for monitored agents and task statuses.
Audit Metadata