mongodb-query-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from the user's database environment to provide optimization advice.
- Ingestion points: Data enters the agent's context through tools like
find(fetching sample documents),explain(retrieving query execution plans), andatlas-get-performance-advisor(accessing slow query logs). - Boundary markers: The skill lacks explicit instructions to treat the data from these tools as untrusted or to use delimiters to prevent instructions within the data from influencing the agent's behavior.
- Capability inventory: The agent possesses tool-calling capabilities that could be misused if influenced by injected instructions, although the skill instructions require user approval for index creation.
- Sanitization: No sanitization or validation of the ingested content is performed before the agent uses it to generate recommendations.
Audit Metadata