agent-mongo
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests data from external MongoDB databases which is then presented to the agent. ● Ingestion points: Untrusted data is retrieved from databases using commands like
query find,query aggregate, andcollection schemaas documented in SKILL.md. ● Boundary markers: The skill does not implement specific delimiters to isolate data retrieved from the database from the agent's instructions. ● Capability inventory: The skill utilizes theBashtool, providing the agent with command execution capabilities. ● Sanitization: There is no mention of sanitization or filtering of database content before it is processed by the agent. - [COMMAND_EXECUTION]: The skill involves the execution of the
agent-mongoCLI via theBashtool to perform database queries and management tasks.
Audit Metadata