diagnose-slow-query
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Processing of Untrusted Database Content: The skill retrieves query text from
sys.query_store_query_text. Because this data is generated by database users, it represents an untrusted ingestion point where malicious instructions could potentially be embedded in the query structure to influence the agent's behavior.\n - Ingestion points: Data is ingested from the
sys.query_store_query_textview as described inSKILL.md.\n - Boundary markers: The skill does not implement specific delimiters or instructions to the agent to disregard instructions potentially contained within the retrieved SQL text.\n
- Capability inventory: The skill utilizes administrative capabilities, including the execution of
sys.sp_query_store_force_planto modify database behavior and various system views for data retrieval.\n - Sanitization: While the database engine performs some normalization (e.g., stripping comments), the skill itself does not apply additional sanitization to the query text before it is processed by the agent.
Audit Metadata