postgresql-expert

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes data retrieved from database queries and logs.
  • Ingestion points: Results from psql commands and output from database monitoring functions described in references/CORE_CONCEPTS.md.
  • Boundary markers: None explicitly defined to separate database-generated content from agent instructions.
  • Capability inventory: The skill is granted access to the Bash tool with psql, pg_dump, pg_restore, createdb, and dropdb, along with Write and Edit permissions.
  • Sanitization: No specific instructions are provided for sanitizing or escaping database output before the agent processes it.
  • [SAFE]: All technical instructions, SQL snippets, and tool usage configurations are consistent with the stated purpose of PostgreSQL database administration. The examples provided for backup, monitoring, and performance tuning follow industry best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 06:42 PM