generate-opal
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical manual for generating OPAL queries, providing clear boundaries, mandatory verification steps, and syntax enforcement. No malicious intent or dangerous patterns were found.
- [COMMAND_EXECUTION]: The skill uses the
observeCLI tool to manage skill content and reference files. These commands are part of the intended platform integration for skill lifecycle management and do not pose a security risk. - [INDIRECT_PROMPT_INJECTION]: The skill addresses the potential for injection by providing rigorous rules for data parsing (e.g.,
parse_json), schema validation, and parameter handling. It instructs the agent to use mapped correlation tags and specific filtering patterns to safely incorporate user-controlled values into queries.
Audit Metadata