Back to skill

Security audit

科技资讯简报

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its news-brief purpose, but it can automatically run an unverified neighboring script and can write output to unrestricted file paths, so it needs review before installation.

Install only if you are comfortable with a Chinese-language tech-news collector that makes public web requests. Before routine use, constrain the output path to a dedicated directory, remove or explicitly verify the neighboring ai-policy-brief execution path, and pin dependencies with a reviewed lock file.

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 (4)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/daily_fetch.py:157
Finding

Arbitrary File Overwrite Through an Unrestricted Output Path

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/daily_fetch.py:45
Finding

Automatic Execution of an Unverified Script From a Sibling Project

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/daily_fetch.py:91
Finding

Untrusted Remote Data Is Written as Unsanitized Active Markdown

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
requirements.txt:3
Finding

Third-Party Dependencies Are Installed Without Exact Versions or Integrity Hashes

Content
View full analysis
=2.28.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 python-dateutil>=2.8.0 feedparser>=6.0.0 ``` The documentation also recommends installation without version constraints: ```bash pip install requests beautifulsoup4 lxml python-dateutil feedparser ``` ### Technical Analysis Every dependency uses a lower-bound constraint rather than an exact reviewed version, and the documented installation command is entirely unconstrained. There are no package hashes, lock files, or trusted package-index restrictions. As a result, two installations performed at different times may resolve to different package versions. Future releases are accepted automatically even though they were not part of this audit. Installation also relies on the package index configured in the execution environment, which may be untrusted or misconfigured. The reviewed dependency names do not show evidence of typosquatting or dependency confusion by themselves. The security issue is the mutable and unverifiable dependency resolution process. ### Attack Path 1. A user follows the installation instructions or installs from `requirements.txt`. 2. `pip` queries its configured package index and resolves the newest versions satisfying the broad constraints. 3. A compromised package release, compromised index, malicious mirror, or unexpectedly vulnerable future version is selected. 4. Package installation hooks or imported package code run in the user's environment. 5. The affected dependency receives the same permissions available to the Python process. ### Impact Assessment A compromised dependency could execute code during installation or runtime with the user's privileges, potentially accessing files, environment variables, and netw ...[truncated 251 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (18)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases are broad, generic, and overlap with ordinary requests for technology news, which can cause the skill to activate when the user did not specifically intend to use it. This creates a scope/intent mismatch that may route general queries into this skill unexpectedly, leading to inappropriate execution, unnecessary network access, or confusing results.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/daily_fetch.py (reported line 49)May include surrounding context.

python
if policy_script.exists():
        import subprocess
        try:
            result = subprocess.run(
                [sys.executable, str(policy_script), '--days', str(days)],
                capture_output=True,
                text=True,

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/sources.md (reported line 73)May include surrounding context.

md
try:
        # B站热门榜
        resp = SESSION.get(
            'https://api.bilibili.com/x/web-interface/popular?ps=20&pn=1',
            timeout=10
        )
        data = resp.json()

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/fetch_trends.py (reported line 150)May include surrounding context.

python
try:
        # B站热门榜
        resp = SESSION.get(
            'https://api.bilibili.com/x/web-interface/popular?ps=20&pn=1',
            timeout=10
        )
        data = resp.json()

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

All user-facing instructions, trigger phrases, and output examples are presented only in Chinese, which implies a fixed language/locale behavior. The file does not state that the skill is region-specific or provide users with an option to choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all headings, labels, and usage-oriented content exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or justification is provided. The file does not indicate that the skill is region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

The dependency is specified with a lower bound only, which allows future installs to resolve to different versions over time. This weakens build reproducibility and can unintentionally introduce vulnerable or incompatible releases into the environment.

Content

Scanner excerpt · requirements.txt (reported line 3)May include surrounding context.

text
# Tech Brief 依赖

requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
90% confidence
Finding

The manifest does not pin requests, and the package has multiple known advisories across versions. Without an exact version, it is impossible to verify whether deployments are using a fixed release, creating uncertainty around exposure to known issues such as credential leakage or TLS-related defects.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

Using an unpinned version range for this package means installations are not deterministic and may pull in newer releases without review. That increases supply-chain risk and makes it harder to ensure that only vetted versions are deployed.

Content

Scanner excerpt · requirements.txt (reported line 4)May include surrounding context.

text
# Tech Brief 依赖

requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
feedparser>=6.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
97% confidence
Finding

An unpinned lxml dependency is risky because different environments may install different releases, including ones with known security issues. Since lxml has historically had security advisories, lack of pinning makes exposure harder to assess and control.

Content

Scanner excerpt · requirements.txt (reported line 5)May include surrounding context.

text
requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
feedparser>=6.0.0

Unverifiable Dependency: lxml has 14 known advisory(ies) (CVE-2021-43818 (lxml's HTML Cleaner allows crafted and SVG embedded scripts to pass through); CVE-2014-3146 (lxml Cross-site Scripting Via Control Characters); CVE-2021-28957 (lxml vulnerable to Cross-Site Scripting ) +11 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
92% confidence
Finding

lxml has a history of security advisories, and because the dependency is unpinned, the actual installed version cannot be verified from this manifest alone. This leaves the project unable to demonstrate that it is consistently using a non-vulnerable release.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
93% confidence
Finding

The package is not pinned to a specific version, so builds are not reproducible and may consume unreviewed future releases. While not directly exploitable by itself, this is a dependency hygiene weakness that can enable supply-chain or stability issues.

Content

Scanner excerpt · requirements.txt (reported line 6)May include surrounding context.

text
requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
feedparser>=6.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
97% confidence
Finding

Leaving feedparser unpinned permits installation of any later version satisfying the lower bound, making the deployed package set unpredictable. Given the package's advisory history, this increases the chance of unintentionally deploying an affected version.

Content

Scanner excerpt · requirements.txt (reported line 7)May include surrounding context.

text
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
feedparser>=6.0.0

Unverifiable Dependency: feedparser has 10 known advisory(ies) (CVE-2011-1157 (feedparser Cross-site Scripting vulnerability); CVE-2009-5065 (feedparser Cross-site Scripting vulnerability); CVE-2011-1158 (feedparser Cross-site Scripting vulnerability) +7 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
92% confidence
Finding

feedparser has known historical advisories, and the lack of version pinning prevents confirmation that only safe releases are installed. This is especially relevant for software that parses external feeds, where parser flaws could be exposed by attacker-controlled content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module docstring and all user-facing descriptions are written in Chinese, which imposes a specific language on users without any visible opt-in or explanation. Under the policy rule, a forced language/locale choice is a natural-language policy concern unless the tool clearly documents that it is intended for a Chinese-only audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code file contains natural-language strings such as the module docstring, dependency error message, and CLI help text in Chinese only. The policy requires avoiding forced language or locale choices unless the skill offers user opt-in or clearly documents the locale restriction.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The module docstring states the script collects hot topics from 微博、知乎、B站, which matches the implemented behavior. However, the nearby '数据源' declaration only lists Weibo and Zhihu, while separate code later performs live requests to Bilibili. This creates an internal documentation/configuration contradiction about what sources the script is intended to use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The Accept-Language header is fixed to 'zh-CN,zh;q=0.9,en;q=0.8', which imposes a specific locale preference in the skill's behavior. Under the policy, locale constraints should either be user-selectable or clearly justified as region-specific.

Content

No source excerpt is available for this finding.