camunda-connectors
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the c8ctl command-line interface to perform its primary tasks, including searching for connector templates, inspecting properties, and applying configurations to BPMN files. These operations are within the scope of the vendor's provided tooling.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @camunda8/cli package from the official NPM registry and fetches configuration schemas from the vendor's GitHub organization. These are well-known and trusted sources associated with the skill author.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests and processes BPMN files and external JSON element templates which could potentially contain malicious instructions if sourced from untrusted locations.
- Ingestion points: BPMN files (e.g., process.bpmn) and JSON element templates loaded via ID, local path, or remote URL.
- Boundary markers: None explicitly mentioned for the content of the processed files.
- Capability inventory: Ability to execute c8ctl commands and perform file-system modifications to BPMN XML files.
- Sanitization: Relies on standard CLI validation and error reporting; no additional sanitization of external content is described.
Audit Metadata