The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the wecom-cli binary to perform all document operations. While these are legitimate uses of the tool provided by the vendor, shell-based command execution always carries a risk of injection if input parameters are not properly sanitized.
[DATA_EXFILTRATION]: The smartpage_create API reads content from local file paths provided in the page_filepath parameter and uploads them to the enterprise WeChat (WeCom) servers. While this is the primary purpose of the skill, it could be used to upload sensitive local files if an attacker can influence the file paths.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (Markdown content) during both creation and export operations.
Ingestion points: Files at page_filepath (SKILL.md, references/smartpage-create.md) and content from smartpage_get_export_result (references/smartpage-export.md).
Boundary markers: None identified in the prompt templates.
Capability inventory: Executes wecom-cli commands, reads local files, and makes network requests via the CLI tool.
Sanitization: None described; the skill directly passes file paths and document IDs to the CLI tool.

wecomcli-smartpage