google-ads-tracking
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script to load business-specific context from adjacent directories.
- Evidence:
python3 ${CLAUDE_SKILL_DIR}/../start-here/scripts/brand_context.py --for google-ads-tracking. - [EXTERNAL_DOWNLOADS]: The skill interacts with well-known Google services to retrieve account information and perform OAuth authentication.
- Evidence: Network requests targeting
googleads.googleapis.comandoauth2.googleapis.com. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface where external content from APIs is processed by the agent, creating a potential vector for indirect prompt injection.
- Ingestion points: Retrieval of conversion actions, goal configurations, and campaign metrics from the Google Ads API.
- Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the structured API data.
- Capability inventory: The skill has the ability to read/write local files (
./campaigns/), execute local scripts, and perform network operations via the Google Ads API. - Sanitization: No explicit sanitization or validation of the retrieved API content is mentioned before it is used to generate reports.
Audit Metadata