Back to skill

Security audit

码虫日报补课系统

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed daily-report helper, but it also includes broad skill install/update/uninstall commands that can change the agent environment beyond the daily-report purpose.

Review this carefully before installing. The reporting tools are understandable, but avoid using the included skills.sh install/update/uninstall helper unless you are comfortable changing installed OpenClaw skills; prefer explicit trusted package names and review workspace paths before running catch-up commands.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
skills.sh:82
Finding

Unrestricted Installation and Update of Unverified Third-Party Skills

Content
View full analysis
&1 echo "" ;; update) echo "" echo -e "${YELLOW}🔄 正在检查更新...${NC}" echo "==========================================" if [ -z "$2" ]; then openclaw skills update 2>&1 | grep -v "^🦞" else openclaw skills update "$2" 2>&1 | grep -v "^🦞" fi ``` ### Technical Analysis The skill-management wrapper permits installation of an arbitrary skill name and supports unpinned updates of either one skill or all installed skills. It does not enforce an allowlist, pin an approved version, verify a package checksum or signature, validate the package source, or require an explicit trust decision after displaying package provenance. Although the skill name is quoted and therefore does not create direct shell command injection, it is passed to a package-management operation that may retrieve and install executable third-party content. The reviewed project is primarily a daily-report utility, so general-purpose dependency installation is broader than the privileges needed for its core reporting functions. The effective behavior of an installed skill may differ from what was previously reviewed if the registry package is compromised, replaced, or updated to a malicious release. ### Attack Path 1. An attacker publishes a malicious skill under a deceptive name, compromises an existing registry package, or gains control of a previously trusted package version. 2. A user or Agent invokes `skills.sh install `, or invokes `skills.sh ...[truncated 1133 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
catch-up.py:245
Finding

Detection-Only Modes Modify Persistent Workspace State

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file documents behaviors that affect user data by stating that missed reports are marked and '补录' is performed, and it also provides a cp command that writes a new report file. Under the markdown-file criteria for SQP-2, the description should clearly warn users that running these actions will create or modify files in their report storage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire template is written in Chinese and presents a fixed language format for the skill output, with no indication that users may choose another language or that the template is intended only for a Chinese-language context. This is a natural-language policy concern because it imposes a specific locale without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This Python file contains its primary docstring, usage text, and later user-facing messages entirely in Chinese, which imposes a specific language on users without offering any locale selection. That matches the language/locale policy violation criteria for natural-language content in any file type.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code sets the HTML document language to zh-CN and uses Chinese-only UI strings in the generated output. Under the natural-language policy rule, forcing a specific language/locale without user opt-in is a policy concern unless the regional restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The banner and descriptions are written in Chinese only, including user-facing positioning such as '管理助手' and '老板友好的技能管理界面'. This imposes a specific language on users without any opt-in, alternative locale, or stated region-specific justification, which matches the language/locale policy-violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file's user-facing natural-language comments and operational note are written exclusively in Chinese, which can constitute a language/locale policy violation when no opt-in, alternative language, or justification for the locale restriction is provided. This is a natural-language issue present directly in the file and applies regardless of the code behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code file contains natural-language strings that force a specific language/locale for docstrings, usage text, and results. Under the policy, locale constraints should either be optional for the user or clearly justified as region-specific; neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This is a natural-language policy issue because the file forces a specific language for its description and console output, and there is no indication that users can opt into another locale. The stated policy allows locale constraints only when justified or when user choice is provided, neither of which appears here.

Content

No source excerpt is available for this finding.