ClawHub
Back to skill

Security audit

Agent Longevity

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed agent-monitoring or scheduling helper with proportionate local logging, and the scanner concerns do not show hidden or harmful behavior.

Install only if you want an agent diagnostic/scheduling skill that may write local decision logs. Keep AGENT_DATA_DIR scoped to a private agent data folder, review or rotate the logs if they may contain sensitive context, and prefer an English or bilingual summary if your operators cannot review the Chinese reference file.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tainted flow: 'LOG_FILE' from os.environ.get (line 21, credential/environment) → open (file write)

Medium
Category
Data Flow
Content
}
    if extra:
        entry["metadata"]["extra"] = extra
    with open(LOG_FILE, "a", encoding="utf-8") as f:
        f.write(json.dumps(entry, ensure_ascii=False) + "\n")
    return entry
Confidence
92% confidence
Finding
with open(LOG_FILE, "a", encoding="utf-8") as f:

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger text is very broad, covering common behaviors such as repetition, loops, degraded output, long-running operation, and memory bloat. That can cause the skill to activate in many loosely related contexts, increasing the chance that an agent follows its guidance unexpectedly or at inappropriate times, especially in autonomous settings where skill selection is automated.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The file is entirely in Chinese without any language choice, translation, or documented locale restriction, which creates an accessibility and reviewability risk for operators who do not read Chinese. In a security-sensitive agent skill, this can hide unsafe logic from maintainers and impair oversight, even though the content here appears operational rather than overtly malicious.

VirusTotal

33/33 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.