Back to skill

Security audit

博客监控

Security checks for vulnerabilities and agentic risk

Overview

This blog-monitoring skill is coherent, but it fetches arbitrary user-provided URLs without network safety limits, so users should review it before installing.

Install only if you trust the environment and will restrict monitored URLs to public blog or RSS endpoints. Avoid localhost, private-network, cloud metadata, or other sensitive URLs, and prefer adding URL validation, request timeouts, response-size limits, exception handling, and pinned dependency versions before use.

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 (3)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:41
Finding

Unrestricted URL Fetching Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:62
Finding

Unbounded Network Requests Can Cause Resource Exhaustion

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:15
Finding

Runtime Dependencies Are Installed Without Version or Integrity Pinning

Content
View full analysis
Remediation
View remediation
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation phrases are very broad ('博客监控 / 网站更新 / 追踪博客') and could trigger the skill in contexts where the user did not clearly intend to invoke external-site monitoring behavior. Because this skill performs network access to user-specified or configured URLs, accidental invocation increases the chance of unintended outbound requests and monitoring actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes monitoring blogs and webpages but does not warn users that it will contact external sites and fetch content from provided URLs. In this context, the code uses requests.get() and feedparser.parse() on supplied URLs, so missing warnings and constraints can lead to unsafe use, including fetching internal, sensitive, or unexpected network resources.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description is written in Chinese, and the rest of the document presents activation phrases and output format only in Chinese, with no indication that another language can be used. This creates a language/locale constraint without user opt-in or documented justification.

Content

No source excerpt is available for this finding.