skills/camunda/skills/camunda-c8ctl/Gen Agent Trust Hub

camunda-c8ctl

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the official Camunda 8 CLI package (@camunda8/cli) via npm and downloads local cluster binaries from Camunda's download infrastructure. These are expected behaviors for the skill's purpose.
  • [COMMAND_EXECUTION]: The skill uses various shell commands to install software, manage local cluster processes, and interact with Camunda 8 APIs. These operations are restricted to the intended CLI functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect injection surface by processing external BPMN and DMN files, as well as user-provided variables.
  • Ingestion points: Processes files through commands like c8ctl deploy and c8ctl run (SKILL.md).
  • Boundary markers: There are no explicit markers or instructions to the agent to ignore potentially malicious content within these files.
  • Capability inventory: The skill can execute commands, perform network requests to clusters, and access local configuration files like profiles.json.
  • Sanitization: The skill does not describe any specific sanitization logic for the content of the process files it handles.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 02:23 AM