camunda-process-mgmt

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes c8ctl commands to perform operations such as deploying resources, starting process instances, and resolving incidents. It explicitly instructs the agent to verify the active cluster profile and use profile flags for mutating commands to ensure cluster safety.
  • [EXTERNAL_DOWNLOADS]: The skill references the c8ctl CLI tool and portability schemas from official vendor repositories on GitHub (e.g., github.com/camunda/c8ctl). These are legitimate resources required for the skill's primary functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external Camunda clusters, which serves as a potential surface for indirect instructions.
  • Ingestion points: The skill retrieves process variables, incident error messages, and task data using commands like c8ctl search variables, c8ctl get inc, and c8ctl list ut in SKILL.md.
  • Boundary markers: The instructions do not specify explicit delimiters or boundary markers for the data ingested from the cluster.
  • Capability inventory: The skill has extensive cluster manipulation capabilities, including resource deployment (c8ctl deploy), instance creation (c8ctl create pi), and task completion (c8ctl complete ut).
  • Sanitization: There is no mention of explicit sanitization or validation of the data received from cluster operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 09:00 PM