agent

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection through its handling of external data.
  • Ingestion points: Natural language questions provided via the command-line interface (args.question in SKILL.md) and data retrieved from the chinook.db database file.
  • Boundary markers: No explicit delimiters or instructions are used in the Python script to separate user input from the agent's system prompt.
  • Capability inventory: The agent utilizes SQLDatabaseToolkit, which allows it to execute SQL queries and explore database schemas (SKILL.md).
  • Sanitization: There is no evidence of input validation or content filtering to prevent malicious instructions embedded in user queries or database records from influencing the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 11:52 AM
Security Audit — agent-trust-hub — agent