add-account-negative-keywords
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download its scripts and configuration files from the author's GitHub repository.
- [COMMAND_EXECUTION]: The skill uses shell commands for setup and requires executing a Python script for its primary operations.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local configuration and baseline files to drive mutations in a live environment.
- Ingestion points: Accesses accounts.json and keyword baseline files to resolve targets and define mutations.
- Boundary markers: Relies on a mandatory human-in-the-loop mutation-safety protocol with dry-run previews and unique approval codes.
- Capability inventory: Mutates Google Ads accounts via the official API, creating SharedSets and adding negative keywords.
- Sanitization: Input keywords are processed as literal strings and stripped of whitespace before being sent to the API.
Audit Metadata