mysql
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches technical documentation and SQL reference guidelines from the PlanetScale GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data, such as database schemas, query plans, and performance metrics, which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Processes database workload constraints, table schemas, and diagnostic command outputs such as EXPLAIN or SHOW STATUS (SKILL.md).
- Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore potentially embedded prompts within the analyzed data.
- Capability inventory: The agent is instructed to suggest and validate significant database operations, including schema modifications like ALTER TABLE, and destructive actions like DROP or TRUNCATE (SKILL.md).
- Sanitization: There are no specific mechanisms for sanitizing or validating the structural database content provided as input before it is interpreted by the agent.
Audit Metadata