ClawHub
Back to skill

Security audit

daily-news

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public news/trend sources and prints a digest, with no evidence of hidden data access, persistence, credential use, or destructive behavior.

Before installing, consider pinning and reviewing the Python dependencies because this skill parses external web and RSS content. The behavior itself is limited to public news retrieval and digest output, so no special local-data or account-access concern is evident.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Unpinned Dependencies

Low
Category
Supply Chain
Content
beautifulsoup4
requests
feedparser
Confidence
92% confidence
Finding
The dependency beautifulsoup4 is unpinned, which makes builds non-reproducible and allows later installs to silently pull newer releases with incompatible changes or newly introduced supply-chain risk. While not an exploit by itself, leaving versions unconstrained weakens dependency hygiene and can expose the skill to malicious or vulnerable upstream releases.

Unpinned Dependencies

Low
Category
Supply Chain
Content
beautifulsoup4
requests
feedparser
Confidence
98% confidence
Finding
The requests dependency is unpinned, and static analysis also indicates the package name is associated with multiple published advisories. Without version pinning, installs may resolve to unsafe versions or inconsistent versions across environments, increasing the chance that known HTTP client flaws affect the skill.

Unpinned Dependencies

Low
Category
Supply Chain
Content
beautifulsoup4
requests
feedparser
Confidence
98% confidence
Finding
The feedparser dependency is unpinned, and the package has multiple historical security advisories. Because no version is specified, the environment may install an insecure release or vary by resolver behavior, which is especially risky for software that parses untrusted feed content.

Known Vulnerable Dependency: requests — 10 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) +7 more

High
Category
Supply Chain
Confidence
97% confidence
Finding
The requirements file includes requests without any version constraint, and static analysis ties that dependency to multiple known advisories affecting certain releases. If the skill performs outbound HTTP requests, vulnerable requests versions can enable credential leakage, TLS/verification issues, or other request-handling flaws when interacting with attacker-controlled URLs or network responses.

Known Vulnerable Dependency: feedparser — 10 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

High
Category
Supply Chain
Confidence
96% confidence
Finding
The requirements file includes feedparser, and the analyzer reports multiple known advisories in that package family, including issues historically related to parsing untrusted feed content. In a skill likely intended to retrieve and parse feeds, this context makes the risk more relevant because attacker-supplied or compromised RSS/Atom content could trigger vulnerable parsing behavior and downstream injection issues.

Static analysis

No suspicious patterns detected.