query-plans

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides educational content and technical guidance for database performance tuning. It contains standard SQL templates for diagnostics and does not include any scripts or executable code.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to interpret external data (PostgreSQL execution plans) provided by the user.
  • Ingestion points: The agent is instructed to read execution plans (e.g., EXPLAIN ANALYZE output) shared by users within the conversation context.
  • Boundary markers: There are no specific instructions for the agent to use delimiters or ignore potentially malicious instructions embedded within the query plan text.
  • Capability inventory: The skill does not define any automated tools, file-system access, or network operations, limiting the potential impact of an injection.
  • Sanitization: No sanitization or validation logic is defined for the input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 12:44 PM
Security Audit — agent-trust-hub — query-plans