wecomcli-contact

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the wecom-cli binary to search for contacts in the corporate directory.
  • Evidence: The skill uses wecom-cli contact users search --json '<JSON 参数>' to retrieve data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the corporate directory which could contain hidden instructions designed to manipulate the agent's behavior.
  • Ingestion points: The users array returned by the CLI (containing names, aliases, positions, and department paths) is ingested into the agent's context (SKILL.md).
  • Boundary markers: Absent. No specific delimiters or "ignore instructions" warnings are provided for the search result data.
  • Capability inventory: The agent has the ability to execute shell commands via wecom-cli and interact with other enabled skills.
  • Sanitization: Absent. The skill does not specify any sanitization, validation, or escaping of the retrieved contact strings before they are presented to the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:04 PM
Security Audit — agent-trust-hub — wecomcli-contact