skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/docx-construction/Gen Agent Trust Hub
docx-construction
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through project dictionaries and file paths in SKILL.md. It lacks boundary markers to delimit user data from instructions and performs no sanitization of input before document interpolation. Capabilities are restricted to filesystem operations.
- [COMMAND_EXECUTION]: The skill uses Python to perform filesystem reads and writes. It requests filesystem permissions in claw.json to manage document templates and output files but does not invoke system shells or external processes.
Audit Metadata