sdd-governanca
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions and SQL code blocks intended for execution via the psql command-line tool to verify database governance constraints.
- [DYNAMIC_EXECUTION]: The skill utilizes SQL templates that are dynamically adapted at runtime. The agent is instructed to replace placeholder table and column names with those discovered in the user's project documentation before execution.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from project definition files.
- Ingestion points: Untrusted data enters the agent context through the reading of project-specific DEFINE files.
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the ingested project files.
- Capability inventory: The skill's environment includes file system access and the ability to execute shell commands.
- Sanitization: There is no explicit sanitization of the content extracted from the DEFINE files before it is used to generate reports or SQL scripts.
Audit Metadata