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 mkdir for folder creation, git clone for repository access, and pip install for the python-docx library.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 06:19 PM
Security Audit — agent-trust-hub — brand-marketing-strategy-proposal-skill