make-scenario-operations
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and process potentially untrusted data from external sources during scenario debugging. \n
- Ingestion points: Untrusted data enters the agent context through
scenario_execution_module_get(retrieves inputs/outputs from cycles) andscenario_trigger_inspect(displays raw webhook delivery payloads). \n - Boundary markers: The skill does not define specific delimiters or instructions to isolate external data, which could lead the agent to follow instructions embedded within inspected logs or payloads. \n
- Capability inventory: The skill possesses capabilities to execute scenarios (
scenario_run) and modify scenario status (scenario_activate), which could be triggered by data-embedded instructions. \n - Sanitization: The instructions do not include any steps for sanitizing or filtering external content before processing. \n- [SAFE]: All tools, such as
scenario_runandscenario_execution_inspect, and external references are consistent with the 'integromat' vendor identity and typical integration platform operations. No evidence of prompt injection, data exfiltration, or obfuscation was found.
Audit Metadata