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

camunda-bpmn

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the @camunda8/cli package via NPM. This is a standard dependency for the Camunda 8 platform and originates from a well-known package registry.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to use shell commands such as c8ctl, find, and grep for file discovery and BPMN validation.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and edit BPMN (XML) files, which serves as an ingestion point for untrusted data that could contain malicious instructions.
  • Ingestion points: The agent reads and modifies .bpmn files from the project directory.
  • Boundary markers: There are no explicit instructions provided to the agent to use specific delimiters or protective prompts when handling the contents of these files.
  • Capability inventory: The agent has access to shell execution via the c8ctl CLI and file system modification tools.
  • Sanitization: The skill relies on c8ctl bpmn lint for structural validation of the XML, but does not specify measures to sanitize or filter potential prompt injection content hidden within the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:28 PM
Security Audit — agent-trust-hub — camunda-bpmn