learn
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard operational patterns for a data-logging tool. It uses defined local paths for configuration (~/.claude-marketing/) and employs a dedicated Python script (intelligence-graph.py) for its logic.
- [DATA_ACCESS]: Reads local brand profiles and agency SOPs to provide context-aware validation. This is consistent with the stated purpose of building a brand-specific intelligence graph.
- [COMMAND_EXECUTION]: Executes a local Python script
intelligence-graph.pylocated within the plugin root. The commands used (--action query-relevant,--action save-learning) are structured and do not indicate arbitrary shell injection or dangerous system operations. - [REMOTE_CODE_EXECUTION]: No external URLs or remote scripts are downloaded or executed. All operations are performed using local resources.
- [PROMPT_INJECTION]: No evidence of instructions designed to bypass safety filters, override system prompts, or extract internal instructions was found.
Audit Metadata