brand-marketing-strategy-proposal-skill
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external client materials (PDF, XLSX, DOCX) to generate marketing strategies, which creates a surface for indirect prompt injection.
- Ingestion points: Client files are read from the
inputs/客户资料/directory for analysis. - Boundary markers: There are no explicit delimiters defined to separate untrusted file content from the agent's system instructions.
- Capability inventory: The skill uses Python scripts to perform local file system reads and write generated reports to the
outputs/folder. - Sanitization: No validation or filtering of input document content is specified in the workflow.- [COMMAND_EXECUTION]: The documentation includes standard setup and maintenance commands, such as
mkdirfor folder creation,git clonefor repository access, andpip installfor thepython-docxlibrary.
Audit Metadata