Back to skill
Skillv1.0.1
VirusTotal security
Tianji · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
ReviewMay 1, 2026, 5:07 AM
- Hash
- a55d5de4a3d05fbf8ceceb27ad65d7ca662a29c00b225f1b772657e67182efa9
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: tianji Version: 1.0.1 The skill includes robust redaction mechanisms in its build script (`scripts/filter-openapi.cjs`) and explicit instructions in `SKILL.md` to prevent the display of sensitive fields like API keys and secrets. However, `SKILL.md` contains a prompt injection vulnerability by instructing the agent to bypass redaction for 'workspace members or audit logs' if the user 'explicitly requests full detail'. The `references/openapi-readonly.json` confirms that the `/workspace/{workspaceId}/members` endpoint can return PII such as user email addresses, which an attacker could exfiltrate by exploiting this instruction.
- External report
- View on VirusTotal