mongodb

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data retrieved from a MongoDB database through mongosh.\n
  • Ingestion points: Results from queries such as db.users.find() (SKILL.md).\n
  • Capability inventory: High-privilege database operations including db.dropDatabase() and filesystem-accessing tools like mongodump and mongoexport (SKILL.md).\n
  • Boundary markers: Absent. There are no explicit instructions to the agent to distinguish between database content and its own instructions.\n
  • Sanitization: Absent. The skill does not provide methods for sanitizing data before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill instructs the agent on using several CLI utilities including mongosh, mongodump, mongoexport, mongoimport, and mongorestore. These tools are used for network communication with database servers and for local file operations during backup and recovery.\n- [DYNAMIC_EXECUTION]: The skill demonstrates the execution of Javascript code within the MongoDB environment using the --eval argument and by loading script files (e.g., mongosh script.js).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 11:43 AM