pipefy-observability
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external sources that could contain malicious instructions designed to influence the agent.
- Ingestion points: The tools
get_ai_agent_logs,get_ai_agent_log_details,get_automation_logs, andget_automation_jobs_export_csvinSKILL.mdingest logs and CSV data from execution histories. - Boundary markers: The instructions do not define clear delimiters or provide the agent with warnings to disregard potential instructions embedded within the log data.
- Capability inventory: The skill possesses the ability to trigger exports (
export_automation_jobs) and modify agent states (toggle_ai_agent_status), creating a potential target for injection attacks. - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the retrieved log or CSV content before it is processed by the agent.
Audit Metadata