Lark/Feishu Sheets & Cloud File Download (with PDF extraction)
Analysis
The skill is coherent and disclosed, but it uses Feishu/Lark app credentials to read/write cloud spreadsheets and auto-installs PDF libraries when needed.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
This script provides:\n- Write cell values to a range (single or batch)\n- Add a new sheet tab\n- Clone an existing sheet's values into a new sheet
The script intentionally exposes cloud spreadsheet mutation operations. This matches the skill purpose, but these actions can change business or shared data.
subprocess.run([sys.executable, "-m", "pip", "install", *packages], check=True, capture_output=True)
The PDF extraction helper can install Python packages dynamically via pip, and the artifacts do not pin package versions. This is disclosed in the README/SKILL and supports the PDF feature, but it relies on external package supply-chain integrity.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Reads Feishu app credentials (appId/appSecret) from ~/.openclaw/openclaw.json to authenticate with the Lark OpenAPI.
The skill needs app credentials to access Feishu/Lark APIs. This is disclosed and purpose-aligned, but app credentials can grant significant tenant-level access depending on configured scopes.
