campaign-status
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several local Python scripts (
campaign-tracker.py,execution-tracker.py, andapproval-manager.py) located within the skill's root directory to retrieve campaign registries, history, and approval queues. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external marketing platforms that could be controlled or influenced by external actors.
- Ingestion points: External data sources include campaign names, performance metrics, and error logs retrieved from connected MCPs such as Google Ads, Meta Marketing, and TikTok Ads, as well as local execution logs.
- Boundary markers: The instructions do not define any delimiters or markers to isolate data retrieved from external platforms from the agent's logic.
- Capability inventory: The skill possesses the ability to execute shell commands via Python scripts and invoke multiple external platform tools.
- Sanitization: There is no explicit sanitization or validation mentioned for the data ingested from external APIs before it is interpolated into the final report output.
Audit Metadata