db-schema-review

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill directly interpolates user-provided arguments into the system prompt. This allows a user to potentially override the agent's senior engineer persona or its safety instructions by including commands within the input arguments.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from schema and migration files, creating an indirect prompt injection surface where instructions hidden in SQL comments or code could influence agent behavior.
  • Ingestion points: Schema and migration files read via the Read and Grep tools (e.g., schema.sql, models.py, schema.prisma).
  • Boundary markers: Absent. The prompt does not utilize delimiters or specific instructions to treat file contents purely as data.
  • Capability inventory: The skill utilizes Read, Grep, and Glob tools to ingest and search file contents.
  • Sanitization: Absent. There is no evidence of filtering or escaping of content extracted from analyzed files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 12:02 AM
Security Audit — agent-trust-hub — db-schema-review