ClawHub
Back to skill

Security audit

paper-lark-report

Security checks across malware telemetry and agentic risk

Overview

This skill is purpose-built for Feishu research reports, but it uses Feishu credentials and creates remote documents automatically with weak safety disclosure and unnecessary token-prefix logging.

Install only if you intend this skill to create Feishu Wiki documents in the configured space. Confirm the target space and parent node, keep Feishu app credentials out of logs and shared prompts, remove token-prefix logging before use, and require manual approval before any scheduled or agent-triggered publication.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly persists fetched paper data and LLM-selected summaries to multiple local files and then publishes results to Feishu Wiki, but the documentation does not clearly warn users that data will be stored on disk and transmitted to an external service. Even if the intended content is research-paper metadata, user-provided research directions, generated analysis, and document URLs/tokens may reveal sensitive project interests or internal workflows when retained or published automatically.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs the skill to obtain Feishu credentials from openclaw.json and use them to request access tokens and call Feishu APIs, but it does not warn users that local credentials will be consumed for outbound network actions. This creates a real risk of unintended credential use, unauthorized document creation, or data egress under the user's Feishu tenant if the skill is installed or triggered without fully informed consent.

Missing User Warnings

Medium
Confidence
99% confidence
Finding
The script prints the Feishu tenant access token to stdout, even if truncated. Secrets written to console output may be captured by shell history tools, CI/CD logs, terminal recorders, centralized logging, or shared debugging sessions, enabling unauthorized API use while the token remains valid. In this skill context, the script is specifically handling live Feishu credentials and creating documents over the network, which makes credential exposure materially more dangerous.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The template explicitly instructs the agent to write a local JSON file, execute Python scripts, and create a remote Feishu document, but it provides no requirement for user confirmation, safety checks, or disclosure that local and remote side effects will occur. In an agent setting, this can cause unauthorized file modification, unintended command execution, or publication of potentially sensitive research content to external systems.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.