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

camunda-forms

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npm install to fetch @bpmn-io/form-json-schema, ajv, and ajv-errors. These are official and well-known packages within the Camunda and BPMN ecosystem, presenting no security risk.
  • [COMMAND_EXECUTION]: Instructions include the use of shell commands (cat, node, npm) to create and run a local validation script. These operations are transparent, limited to the project directory, and serve a legitimate developer purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of user-facing form labels and descriptions. While this is a common surface for indirect injection, the skill's specific focus on Camunda's schema structure and its use of standard validation tools makes it benign in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:12 PM
Security Audit — agent-trust-hub — camunda-forms