ClawHub
Back to skill

Security audit

feishu paper manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent paper-management workflow guide that discloses its Feishu storage and metadata-table behavior, with no executable code or hidden persistence.

Install only if you want a Feishu-based paper library that stores papers, links, message metadata, summaries, and tags in durable Feishu docs and tables. Configure bot permissions, retention, sharing access, and consent expectations before using it with private chats, confidential manuscripts, or restricted links.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the system to ingest Feishu messages, download PDF attachments or external links, and store both files and metadata in Feishu cloud docs and tables, but the top-level description does not warn users about this data collection and persistence. This can lead users to invoke the skill without understanding that message content, sender metadata, timestamps, links, and attached papers may be copied into durable storage, increasing privacy, consent, and data-governance risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The default prompt broadly instructs use of the skill for both design and implementation of a Feishu/OpenClaw workflow without clear activation boundaries or safety constraints. In agent ecosystems, such broad prompts can cause over-invocation or use in contexts the author did not intend, increasing the chance of unintended actions against Feishu content, cloud docs, or metadata tables.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow explicitly ingests papers from Feishu messages, uploads PDFs to cloud storage, and writes metadata into a searchable table, but it provides no user-facing notice about persistence, retention, or where content is stored. In this skill context, users may paste copyrighted, confidential, or sensitive research material, so silent storage and indexing increases privacy, compliance, and data-governance risk even if the implementation is otherwise intended for normal document management.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This flow sends user-provided PDFs or source URLs to OpenClaw for ingestion and metadata extraction without warning that external processing will occur. In the paper-management context, that can expose proprietary manuscripts, private links, tokens embedded in URLs, or sensitive research context to another service, creating confidentiality and compliance risks if users are unaware of the transfer.

Content

No source excerpt is available for this finding.