Back to skill
Skillv1.0.0
VirusTotal security
Poe Api · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
BenignApr 30, 2026, 4:58 AM
- Hash
- efaff65386a97bb1da1ec0159260f4777782c21d8f2de9b16879a16d6ce13f25
- Source
- palm
- Verdict
- benign
- Code Insight
- Type: OpenClaw Skill Name: innotech-poe-api Version: 1.0.0 The OpenClaw AgentSkills skill bundle for Poe API orchestration is benign. All files consistently describe and implement a skill for intelligently querying various AI models via the Poe API. The `scripts/poe_client.py` code correctly handles API keys via environment variables, interacts solely with the specified Poe API endpoint, and does not contain any malicious functions like shell execution, arbitrary file system access, or unauthorized network calls. The documentation (`SKILL.md`, `README.md`, `MODEL_SELECTION_GUIDE.md`) provides clear, helpful instructions for the AI agent, including security best practices (e.g., 'NEVER hardcode API keys', 'Do NOT use this skill for: ... Local file operations, System commands'), and contains no evidence of prompt injection attempts against the OpenClaw agent itself. The potential for prompt injection exists against the AI models being queried, but this is an inherent characteristic of any LLM interaction and not a malicious flaw in the skill's implementation.
- External report
- View on VirusTotal