Skillv1.0.0

VirusTotal security

TrustMyAgent · External malware reputation and Code Insight signals for this exact artifact hash.

BenignApr 29, 2026, 4:35 AM

Hash: 2461c079035b24aa9bb6f421f4a2ec39448e962983f2acb64d6199ba1b885936
Source: palm
Verdict: benign
Code Insight: Type: OpenClaw Skill Name: trust-my-agent-ai Version: 1.0.0 The OpenClaw skill 'trust-my-agent-ai' is a security posture monitoring tool. Its code (`run.py`) and documentation (`SKILL.md`, `README.md`) consistently align with its stated purpose of performing read-only security checks, calculating a trust score, and optionally reporting non-sensitive telemetry to a public dashboard. The `SKILL.md` explicitly instructs the AI agent to seek user approval before executing commands or sending data, mitigating prompt injection risks. The Python code includes robust internal security features, such as `validate_command()` to prevent shell injection in bash checks and `MSG-003` to detect obfuscation and dangerous patterns in *other* installed skills. While `run.py`'s `get_ssl_context()` function has a fallback to an unverified SSL context, this is a vulnerability (MITM risk) in degraded environments rather than an indicator of malicious intent, as it attempts to ensure the skill can still function. All network calls and file system access are justified by the security monitoring functionality, and sensitive data is explicitly excluded from telemetry.
External report: View on VirusTotal