sop-creator
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill logic is entirely text-based and focused on document generation. It does not perform any command execution, file system modifications (other than reading a context file), or network requests.
- [DATA_EXPOSURE]: The skill attempts to read a file named
FOUNDER_CONTEXT.mdfrom the project root. This is used to personalize the generated SOP with business-specific details. This is a local read operation within the agent's workspace and does not involve exfiltrating data to external servers. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to describe business processes. However, because the skill lacks dangerous capabilities—such as shell execution, arbitrary code evaluation, or network access—the risk of an indirect prompt injection attack causing harm is negligible.
- [COMMAND_EXECUTION]: There are no subprocess calls or system commands present in the skill definition.
Audit Metadata