The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing multiple CLI tools such as wechatsync and biliup to perform network uploads and platform synchronization.
[EXTERNAL_DOWNLOADS]: The skill references and encourages the use of third-party external repositories and tools, specifically xpzouying/xiaohongshu-mcp and Nemo2011/bilibili-api, which are not part of the standard trusted vendor lists.
[PROMPT_INJECTION]: The skill processes external article files (e.g., article.md) as primary input, which creates a surface for indirect prompt injection if the source content contains malicious instructions intended to influence the agent's behavior during the adaptation or synchronization process.
Ingestion points: The source_file or topic parameters allow loading external content into the agent context (File: SKILL.md).
Boundary markers: The instructions do not specify explicit delimiters or 'ignore' warnings for the input content.
Capability inventory: The agent has the capability to execute shell commands (wechatsync, biliup) and Python scripts (for bilibili-api-python).
Sanitization: There is no mention of sanitizing or filtering the input article content before it is processed by style specialists or toolchain orchestration scripts.
[COMMAND_EXECUTION]: The technical deliverables include Python code templates (File: SKILL.md) that involve importing and utilizing the bilibili_api library, requiring the agent to generate and execute local script content.

agency-multi-platform-publisher