oma-db

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its interaction with codebase files and local execution capabilities.
  • Ingestion points: The agent is instructed to read existing database schemas, migration files, query logs, and workload descriptions from the codebase (SKILL.md, resources/execution-protocol.md).
  • Capability inventory: The agent has the authority to write documentation and migration files to the local file system and execute shell commands including ripgrep and project-specific migration or query-plan tools (SKILL.md, resources/execution-protocol.md).
  • Boundary markers: No specific delimiters or instructions are provided to help the agent distinguish between its core instructions and potentially malicious instructions embedded in the project files it analyzes.
  • Sanitization: There is no evidence of content sanitization or validation for the data ingested from the codebase.
  • [COMMAND_EXECUTION]: The skill instructions include the use of shell commands to interact with the project environment.
  • Evidence: The agent uses rg (ripgrep) to discover database-related files and is prompted to execute project-specific migration, query-plan, or retrieval-quality commands after identifying the database engine (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:52 PM