database-review

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill primary function is the static analysis of local configuration and source files (e.g., schema.prisma, models.py, migration files) to provide database optimization recommendations.
  • [SAFE]: Telemetry logging is performed locally within the agent's internal project directory (~/.claude/projects/) and does not involve communication with external servers or exfiltration of sensitive information.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its analysis of untrusted codebase content.
  • Ingestion points: The entire local codebase, including migration files, ORM schemas, and source code.
  • Boundary markers: Absent; the skill does not use specific delimiters to isolate processed code from instructions.
  • Capability inventory: Local file reading and writing of telemetry logs to a known directory.
  • Sanitization: Absent; the skill does not explicitly sanitize or escape the content it reads before processing.
  • Context: This is documented as an inherent architectural surface of the skill's review functionality (Category 8) and is considered safe given the lack of network or high-privilege execution capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:58 AM
Security Audit — agent-trust-hub — database-review