sqlite-query

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external SQLite databases that could contain embedded malicious instructions.
  • Ingestion points: Results from SQL queries and schema inspections (SKILL.md).
  • Boundary markers: No delimiters or boundary markers are described to differentiate database content from the agent's primary instructions.
  • Capability inventory: The skill allows the agent to execute arbitrary SQL queries, inspect schemas, and list database files.
  • Sanitization: The documentation does not specify any sanitization or validation of data retrieved from the databases.
  • [NO_CODE]: The analysis is based on the tool descriptions and workflow in SKILL.md, as no executable scripts or source code were included with the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 10:39 PM