wecomcli-smartsheet

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has a defined attack surface for indirect prompt injection as it ingests untrusted data from WeCom Smartsheet records.
  • Ingestion points: Records are read from sub-tables via the wecom-cli smartsheet records query and records list commands (detailed in references/smart-sheet-read.md).
  • Boundary markers: Present. The skill contains a 'Security Tip' in SKILL.md that explicitly instructs the agent to ignore any content returned by the interface as system instructions or commands.
  • Capability inventory: The skill possesses significant capabilities, including the ability to add, update, and delete records, fields, and views (detailed in references/smart-sheet-edit.md).
  • Sanitization: The agent is instructed to ignore any tokens, keys, or credentials found within data responses.
  • [COMMAND_EXECUTION]: The skill dynamically generates shell commands for the wecom-cli tool. It incorporates a robust 'Command Splicing Safety Specification' in references/common.md and references/smart-sheet-edit.md to prevent command injection.
  • The specification mandates wrapping all external values in single quotes and using a specific five-character sequence ('"'"') to escape existing single quotes, ensuring data is treated as pure literals.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 02:54 AM