data-write-query
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides purely instructional content for generating SQL queries and does not contain any malicious instructions, obfuscated commands, or external network dependencies. It promotes secure practices such as avoiding 'SELECT *' and filtering data early.\n- [NO_CODE]: This skill consists entirely of a markdown instruction file (SKILL.md) and does not include any executable scripts, binaries, or configuration files that could hide malicious logic.\n- [PROMPT_INJECTION]: The skill processes natural language descriptions from users to generate SQL, which represents a surface for indirect prompt injection. This is a functional requirement of the skill's primary purpose.\n
- Ingestion points: The 'description' parameter in the Usage section of SKILL.md.\n
- Boundary markers: None present in the current instructions to delimit user-provided content.\n
- Capability inventory: Mentions of searching tables, inspecting schema, and potentially executing queries if a data warehouse tool is connected (SKILL.md steps 3 and 6).\n
- Sanitization: No specific sanitization or escaping instructions are provided for the user-supplied business logic.
Audit Metadata