rental-assistant

Warn

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install external software using Homebrew from a third-party tap (brew tap xpzouying/agent-cli and brew install xpzouying/agent-cli/xiaohongshu-cli). The source repository belongs to an individual user and is not affiliated with the skill author's organization or a recognized trusted vendor, posing a supply chain risk.
  • [COMMAND_EXECUTION]: The skill's primary functionality relies on the execution of multiple local CLI tools (58-cli, anjuke-cli, apartments-cli, rightmove-cli, idealista-cli, xiaohongshu-cli). It also requires a specific daemon to be active at ~/.kimi-webbridge/bin/kimi-webbridge and suggests using another skill to start it if it is not running.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content retrieved from various external rental websites. Malicious listings could potentially contain instructions designed to manipulate the agent's behavior during the comparison or analysis phase.
  • Ingestion points: Data returned by rental CLI tools (e.g., listing descriptions, titles) as described in SKILL.md.
  • Boundary markers: Absent. The instructions do not include delimiters or specific warnings to ignore instructions embedded within the rental data.
  • Capability inventory: The agent has the ability to execute shell commands and perform network operations via the listed CLI tools.
  • Sanitization: Absent. There is no evidence of filtering or escaping logic for the external content before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 15, 2026, 02:39 AM