signals-scout-data-pipelines
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes logs and error messages that may contain untrusted content from external systems. \n
- Ingestion points: Data enters via
cdp-functions-logs-retrieve,workflows-logs, andworkflows-list-invocations(SKILL.md). \n - Boundary markers: The instructions explicitly warn the agent to treat log content as data rather than instructions and suggest using short untrusted snippets (SKILL.md). \n
- Capability inventory: The skill uses tools to execute SQL queries and emit signals (SKILL.md). \n
- Sanitization: The agent is instructed to truncate long messages and remove payload echoes before processing.
Audit Metadata