pscale-sql
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to facilitate the execution of the
pscale sqlcommand. This involves running shell commands with user-supplied arguments such as<database>,<branch>,<org>, and<query>. These commands interact with external database infrastructure and can modify data depending on the provided flags. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests untrusted data from the user to fill placeholders for database, branch, organization, keyspace, and database names, as well as the SQL query itself in
SKILL.md. - Boundary markers: Absent. The skill provides command templates but does not specify how the agent should delimit or escape user input to prevent command injection into the shell environment.
- Capability inventory: The skill has the capability to execute shell commands (
pscale sql) which can perform read/write operations on remote databases. - Sanitization: Absent. There are no instructions for validating, escaping, or sanitizing the user-provided strings before they are interpolated into the CLI command.
Audit Metadata