sql-pro
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process untrusted external data including query goals, database schemas, and workload descriptions.
- Ingestion points: The
argument-hintfield inSKILL.mdand the Phase 1 workflow explicitly instruct the agent to process external query goals and schema details. - Boundary markers: The instructions do not define clear boundary markers (such as XML tags or triple backticks) to separate user-provided data from system instructions, nor do they include warnings to ignore instructions embedded within the processed data.
- Capability inventory: The skill is restricted to the
Readtool in its frontmatter, which significantly limits the potential impact of a successful injection compared to skills with write or network access. - Sanitization: There are no defined procedures for validating or escaping external content before it is processed by the agent.
Audit Metadata