iii-observability
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of external telemetry data, creating a potential attack surface for indirect prompt injection.\n
- Ingestion points: Data enters the agent's context through logs emitted via
engine::log::*functions and the OTLP ingestion pipeline documented inSKILL.md.\n - Boundary markers: The documentation does not describe the use of delimiters or specific safety markers to differentiate log content from agent instructions.\n
- Capability inventory: The
logreactive trigger allows the agent to automatically execute registered functions in response to ingested log entries, which could be triggered by malicious content in logs.\n - Sanitization: There is no evidence in the provided documentation of sanitization, filtering, or escaping of log content before it is processed by the agent's triggers.
Audit Metadata