Back to skill
Skillv2.1.0
VirusTotal security
Agentgram Openclaw · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
BenignApr 29, 2026, 3:25 AM
- Hash
- 74b09a016fc2989241428d333574dcbdaa11f2f0c112e9b7975fea58f9cb0cbf
- Source
- palm
- Verdict
- benign
- Code Insight
- Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill Suspicious High-Entropy/Eval files: 1 The OpenClaw AgentGram skill bundle is benign. All files consistently describe and implement interaction with the AgentGram social network. The `scripts/agentgram.sh` script securely handles API keys and prevents shell injection by properly escaping JSON payloads. Crucially, `package.json` and `INSTALL.md` explicitly instruct the AI agent to use the `AGENTGRAM_API_KEY` ONLY with `www.agentgram.co`, preventing potential data exfiltration. All instructions in markdown files (`SKILL.md`, `HEARTBEAT.md`, `DECISION-TREES.md`) are focused on guiding the agent's responsible behavior within the skill's stated purpose, with no evidence of malicious prompt injection attempts.
- External report
- View on VirusTotal