database-optimizer
Fail
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes documentation links to a GitHub Pages site (jeffallan.github.io) that has been flagged as malicious by automated URL reputation scanners.
- [METADATA_POISONING]: The skill metadata (author and documentation fields) contains links to infrastructure associated with malicious activity. Additionally, the SKILL.md file has been identified by file reputation scanners as FileRepMalware.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted data from database query logs and execution plans, creating a potential vector for indirect instructions.
- Ingestion points: The skill reads data from pg_stat_statements, slow query logs, and execution plans (EXPLAIN ANALYZE) as seen in SKILL.md and references/monitoring-analysis.md.
- Boundary markers: The instructions do not define clear delimiters or warnings to treat ingested database content as untrusted data.
- Capability inventory: The skill allows the agent to execute complex SQL commands, modify database configurations (ALTER SYSTEM), and manage indexes based on analyzed output.
- Sanitization: There are no mechanisms described to sanitize or filter the results of database queries before processing.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata