Back to skill
Skillv1.2.1
VirusTotal security
Skill · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
BenignApr 30, 2026, 4:27 AM
- Hash
- 28311a5213e4349bef06d3e73c7ecce9d7f4c912ea76e41a6ab81db498d4ae56
- Source
- palm
- Verdict
- benign
- Code Insight
- Type: OpenClaw Skill Name: claude-watchdog Version: 1.2.1 The OpenClaw AgentSkills skill bundle 'claude-watchdog' is classified as benign. The code and documentation align with its stated purpose of monitoring the Claude API and sending Telegram alerts. Sensitive configuration (tokens) is handled securely by writing to a file with `600` permissions (`claude-watchdog.env`), and user inputs in `scripts/setup.sh` are validated (e.g., numeric chat/topic IDs) before being used in `curl` commands or written to config. Network activity is confined to legitimate endpoints: `api.telegram.org` for alerts, `status.claude.com` for status checks, and `127.0.0.1` for local gateway latency probes. There is no evidence of data exfiltration, unauthorized persistence, arbitrary code execution, or prompt injection attempts against the AI agent in `SKILL.md`.
- External report
- View on VirusTotal