db-tool
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
bunruntime to execute thedb-toolutility for database interactions, environment management, and schema introspection. - [INDIRECT_PROMPT_INJECTION]: The skill processes data returned from SQL queries (e.g.,
SELECT * FROM users), which represents an attack surface where untrusted data from a database could influence agent behavior. - Ingestion points: SQL query results returned by
bun db-tool sql(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined in the skill instructions.
- Capability inventory: The agent can execute database commands and list environments via the
db-toolCLI (SKILL.md). - Sanitization: No explicit sanitization or filtering of database output is mentioned.
Audit Metadata