aps-doc-master-segment
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
tdxCLI (via a Bash tool) andmcp__treasuredata__*tools to perform database operations, such astdx use,tdx tables, andtdx describe. These commands are necessary to discover schemas and extract metadata for documentation purposes. - [PROMPT_INJECTION]: The skill processes data from external database schemas, which serves as an ingestion point for potential indirect prompt injection.
- Ingestion points: Metadata retrieved through schema discovery commands in the SKILL.md file.
- Boundary markers: No specific delimiters or safety instructions are used to separate untrusted database content from the documentation template.
- Capability inventory: Access to CLI tools and MCP server functions for database interaction.
- Sanitization: Database metadata (such as column names and table descriptions) is incorporated into the output without explicit validation or escaping.
Audit Metadata