ClawHub
Back to skill

Security audit

report-search

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently searches and retrieves fxbaogao research reports, with one optional TLS troubleshooting setting users should treat cautiously.

Install only if you are comfortable sending report search terms and selected document IDs to fxbaogao.com. Do not set FXBAOGAO_SSL_NO_VERIFY=1 except for short local troubleshooting, because it disables server certificate checks and can let an intercepted connection return misleading report data.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/fxbaogao_client.py:242
Finding

Optional TLS Certificate Verification Bypass

Content
View full analysis
ssl.SSLContext: if SSL_NO_VERIFY: return ssl._create_unverified_context() if certifi is not None: return ssl.create_default_context(cafile=certifi.where()) return ssl.create_default_context() ``` The insecure mode is recommended as a certificate-error workaround in `SKILL.md:86`: ```markdown - 如果运行时出现本机 Python 证书链错误，可提示用户临时加上 `FXBAOGAO_SSL_NO_VERIFY=1` 重试，但不要默认关闭 SSL 校验 ``` ### Technical Analysis When `FXBAOGAO_SSL_NO_VERIFY` is set to a recognized true value, `_build_ssl_context()` returns `ssl._create_unverified_context()`. This disables both certificate-chain validation and hostname verification for requests made through the shared client. The affected requests include report-search API calls to the configured API endpoint and report-detail requests to the configured detail endpoint. Although verification remains enabled by default, the Skill explicitly documents disabling it as a troubleshooting procedure. A user encountering a local certificate-chain error may therefore enable this mode and continue using it beyond the immediate test. Without certificate validation, HTTPS still encrypts traffic but no longer authenticates the remote server. An attacker capable of intercepting or redirecting network traffic can present an arbitrary certificate and impersonate the report service. ### Attack Path 1. The user encounters a Python certificate-chain error when ...[truncated 1414 chars]
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

Tainted flow: 'request' from os.getenv (line 205, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/fxbaogao_client.py (reported line 214)May include surrounding context.

python
ssl_context = _build_ssl_context()

    try:
        with urllib.request.urlopen(
            request,
            timeout=HTTP_TIMEOUT,
            context=ssl_context,

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
运行脚本时，脚本路径要相对当前 `SKILL.md` 所在目录解析，不要假设当前工作目录正好在 skill 目录内。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description and user-facing instructions are entirely written in Chinese and state the skill's behavior in that locale without indicating that users may choose another language. Under the policy, a skill should not impose a specific language unless it offers opt-in or clearly documents a justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file presents all invocation examples and user-facing response guidance only in Chinese. Under the policy-violation category, forcing a specific language without user opt-in can be a locale/language policy issue when no alternative or opt-in is provided.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The code allows TLS certificate verification to be disabled globally via the FXBAOGAO_SSL_NO_VERIFY environment variable, causing _build_ssl_context() to return an unverified SSL context. If enabled, requests to the API and detail site become vulnerable to man-in-the-middle interception and tampering, which is especially dangerous because remote JSON and HTML content are trusted and parsed into results.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file contains user-facing error and output strings in Chinese, such as the validation message here, without offering any language selection or documenting that the skill is intentionally Chinese-only. This can violate language/locale policy because the skill imposes one language on all users by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This shell script contains user-facing messages and comments entirely in Chinese, including status and error output shown during execution. For a general-purpose skill validator, forcing a specific language without user opt-in or documented locale justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code file contains user-facing natural-language strings such as the parser description, examples, and argument help text exclusively in Chinese. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code file contains user-facing documentation and runtime messages in Chinese only, including the module docstring and printed status text. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no language choice or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown template presents all headings and instructions in Chinese and does not indicate that the user can choose another language. The policy scope includes language or locale constraints, and here the skill appears to force a specific language without explicit user opt-in or justification.

Content

No source excerpt is available for this finding.