Back to skill
Skillv1.1.0
VirusTotal security
Consilium · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 30, 2026, 4:30 AM
- Hash
- 9ca3115193e45ca9d118ad958c314152cbe3b1057c2436594c4996742be5aa76
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: consilium Version: 1.1.0 The skill is classified as suspicious due to a significant prompt injection vulnerability against its sub-agents. The `references/PROTOCOL.md` file reveals that user input (`{question}`) and potentially user-controlled `lens_description` (via flags described in `SKILL.md`) are directly embedded into the prompt template for spawned sub-agents. This allows a malicious user to craft inputs that could manipulate sub-agent behavior, potentially leading to unintended actions or information disclosure if the sub-agents have access to sensitive tools or data. While the skill's stated purpose is benign and it explicitly denies external dependencies or data exfiltration to unauthorized endpoints, this vulnerability represents a high-risk capability without clear malicious intent from the developer.
- External report
- View on VirusTotal