spell-reference
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill contains documentation for compiling and running a local command-line tool (
sw-spell). These instructions are purely for internal data retrieval and do not include any malicious, arbitrary, or high-privilege command patterns. - DATA_EXFILTRATION (SAFE): No network operations, external connections, or access to sensitive local file paths (e.g., credentials or SSH keys) were found.
- PROMPT_INJECTION (SAFE): The markdown content consists solely of instructional and descriptive text for spell data; it contains no attempts to override the agent's system prompt or bypass safety filters.
Audit Metadata