wecom-smartsheet-data

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests data from external smartsheets which could contain malicious instructions.
  • Ingestion points: Data is retrieved from external sheets using the smartsheet_get_records function as described in SKILL.md and references/api-get-records.md.
  • Boundary markers: There are no instructions or delimiters defined to separate untrusted data from the agent's system instructions or to ignore embedded commands.
  • Capability inventory: The skill possesses powerful capabilities to modify or delete data via smartsheet_add_records, smartsheet_update_records, and smartsheet_delete_records.
  • Sanitization: The documentation does not specify any sanitization or validation of the text content retrieved from cells before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill functions by executing system commands through the wecom_mcp CLI tool. This allows the agent to perform administrative document operations based on natural language inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 11:40 AM