skill-creator
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill documentation includes examples of platform-specific shell execution syntax for capturing environment snapshots. This is an instructional component for developers authoring new skills and does not contain malicious code or unauthorized access patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing and rewriting skill draft files. It mitigates risks associated with processing untrusted data by including explicit guardrails that prevent the agent from accidentally exposing or replacing user secrets, API keys, or certificates.
- [COMMAND_EXECUTION]: The skill utilizes a local JavaScript grader and provides instructions for using vendor-specific CLI tools (Capgo CLI) via npx. These operations are consistent with the skill's primary purpose of development and validation.
Audit Metadata