db-explore

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run mongosh commands for database interaction.
  • [DATA_EXFILTRATION]: The skill provides instructions to query the users collection, which is explicitly described as containing player authentication data. Reading this information into the agent's context presents a data exposure risk.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from the database without sanitization.
  • Ingestion points: Database results from collections such as users, clans, and bases are read into the context via mongosh.
  • Boundary markers: Absent; no delimiters are used to separate database output from instructions.
  • Capability inventory: The skill utilizes the Bash tool to execute commands.
  • Sanitization: Absent; no validation or filtering of the database content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 03:23 PM
Security Audit — agent-trust-hub — db-explore