we-media-content-studio
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local Python utility script (
workspace.py) to automate the creation of directory structures, topic archives, and versioned Markdown files. The execution is scoped to the skill's own internal script and current working directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill establishes an environment for ingesting and processing content-related data, such as niche descriptions and audience feedback, which are stored in Markdown and CSV files.\n - Ingestion points: Data enters via script arguments and when reading from the ledger (
选题台账.csv) and feedback (反馈.csv) files.\n - Boundary markers: The system utilizes structured Markdown headers, CSV tabular formats, and JSON keys to isolate specific data points and instructions.\n
- Capability inventory: The skill possesses capabilities for local file system operations (creating directories, copying files, writing text) and executing its internal helper script.\n
- Sanitization: Path sanitization is implemented for directory names to prevent filesystem navigation issues, though general text inputs are treated as literal strings for content creation.
Audit Metadata