ga4-lead-quality-investigation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external Google Ads and GA4 APIs to generate recommendations, which introduces a potential surface for malicious data to influence agent behavior. 1. Ingestion points: Outputs from the query_campaign_settings.py script and GA4 query scripts defined in the Script Contract. 2. Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the API responses. 3. Capability inventory: The skill utilizes Bash for command execution, Write for document generation, and the Skill tool for modular framework invocation. 4. Sanitization: No explicit sanitization, escaping, or validation steps for the ingested API data are described.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run local Python scripts (e.g., query_campaign_settings.py) and interpolates user-supplied values like CUSTOMER_ID and CAMPAIGN_NAME directly into the shell command. This pattern can be exploited if the inputs are not properly sanitized by the underlying execution environment.
Audit Metadata