surrealdb-migrate

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to execute local TypeScript migration scripts (e.g., bun run scripts/surrealdb-migrate.ts) and interact with database instances via curl and the surreal CLI.
  • [PROMPT_INJECTION]: The skill processes user-supplied backup files and schema directories as ingestion points, which creates an indirect prompt injection surface where malicious instructions embedded in the data could influence agent behavior.
  • Ingestion points: User-provided backup files and schema directories (SKILL.md)
  • Boundary markers: Absent in instructions.
  • Capability inventory: Read, Grep, Bash, Glob, Edit, and Write (SKILL.md frontmatter).
  • Sanitization: Not explicitly implemented; the skill scans and processes content without described sanitization logic.
  • [CREDENTIALS_UNSAFE]: The documentation includes example bash commands with hardcoded default credentials (root:root) used for basic authentication in database export and import operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:47 PM
Security Audit — agent-trust-hub — surrealdb-migrate