retargeting-strategy
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
campaign-tracker.pyto list and review existing campaign data. This is a functional requirement for the skill to understand historical performance and does not involve untrusted remote execution. - [DATA_EXPOSURE]: The skill reads local JSON configuration files located in the user's home directory (
~/.claude-marketing/). These files contain brand profiles, voice guidelines, and marketing templates necessary for the skill's primary purpose. No sensitive credentials or system files are accessed. - [INDIRECT_PROMPT_INJECTION]: The skill processes website traffic volume and funnel data provided by the user. While this represents an ingestion point for external data, the skill uses it for strategy calculation rather than executable commands, and the risk is minimal.
Audit Metadata