kaggle-playbook
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to verify platform metrics by fetching data from external Kaggle pages, such as community threads and documentation. This content is untrusted and could contain injection attempts meant to influence the agent's reasoning.\n
- Ingestion points: External Kaggle community threads and platform documentation (SKILL.md).\n
- Boundary markers: The instructions do not specify the use of delimiters for the fetched web content.\n
- Capability inventory: The agent generates marketing plans and Python code snippets for data science notebooks.\n
- Sanitization: No specific sanitization or filtering is prescribed for data retrieved from the platform.
Audit Metadata