deck-guizang-editorial
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses instructions returned from the 'prepare_open_design_brief' tool to author files. This creates a vector where malicious instructions embedded in the tool's response could influence the agent's file-editing actions.
- Ingestion points: The output of 'prepare_open_design_brief' referenced in SKILL.md.
- Boundary markers: No specific delimiters or safety warnings are provided for the tool output.
- Capability inventory: Uses the agent's file-editing tools to create or modify files based on the returned instructions.
- Sanitization: No sanitization or validation logic is defined for the external content before processing.
Audit Metadata