database-test-helper
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requests to assist with test automation tasks, creating a potential surface for indirect prompt injection.
- Ingestion points: User input triggers in
SKILL.md(e.g., "database test helper", "database helper", "database"). - Boundary markers: None identified to distinguish user-provided data from system instructions or to instruct the agent to ignore embedded commands.
- Capability inventory: The skill is permitted to use
Bash(cmd:*),Write,Edit,Read, andGreptools via theallowed-toolsconfiguration. - Sanitization: No sanitization, validation logic, or escaping mechanism is specified for input data before it is processed by the agent or passed to tools.
Audit Metadata