War Intelligence Monitor

Real-time war intelligence monitoring and emergency alert system for conflict zones. Use when user needs to track military conflicts, receive emergency alert...

This skill can collect and repeatedly transmit sensitive data (exact location, emergency contacts) and instructs the agent to create cron jobs that run autonomously and may post to external channels. Before installing or running: (1) Confirm exactly which endpoints the agent will use to send alerts; prefer single-purpose inbound webhooks or channels you control and require tokens. (2) Do not provide precise home coordinates or unneeded personal phone numbers until you trust the destination. (3) Require explicit, interactive confirmation before creating any cron jobs; review the actual crontab entries the agent will add. (4) If posting to Discord/Telegram, create minimal-scope webhooks/bots and rotate tokens after testing. (5) Consider running the skill in a sandboxed environment or on a disposable account until you confirm its behavior. If the publisher can provide a concrete list of APIs/endpoints and an explicit auth model (what keys/hooks are needed and where data will be sent), reassess — that information would raise confidence toward benign.

Type: OpenClaw Skill Name: war-intel-monitor Version: 1.0.0 This skill is classified as suspicious due to its requirement for extensive high-risk capabilities, although these are plausibly needed for its stated purpose. The skill instructs the agent to perform actions such as creating scheduled cron jobs for monitoring, accessing external network resources (news, flight data, airspace status) for information gathering, and sending alerts to external messaging services (e.g., Discord/Telegram) as specified in `SKILL.md` and `references/setup-guide.md`. It also requires reading sensitive personal data (user location, emergency contacts) from `config.json` (template in `references/config-template.json`). While there is no clear evidence of intentional malicious code or explicit prompt injection to subvert the agent's core function, the broad permissions and data handling requirements present a significant attack surface if the underlying agent implementation has vulnerabilities (e.g., shell injection in cron creation, insecure network handling).