Back to skill

Security audit

Trend Watcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a GitHub trend-watching utility with disclosed local bookmarking behavior and no evidence of hidden execution, credential access, exfiltration, or destructive actions.

Before installing, expect the skill to contact GitHub when run and to keep bookmark data locally if its bookmark helper is used. The documentation should be tightened around the bookmark CLI behavior and storage path, but the observed behavior is coherent with a trend-monitoring and bookmarking utility.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises integrations with external services and local logging/bookmark files but does not warn users that running it may send data to GitHub/Feishu or persist data into local files or memory logs. This is not an exploit by itself, but it creates a transparency and privacy risk because users may unknowingly trigger outbound network access and local data retention.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The top-level documentation describes the tool as monitoring GitHub Trending for emerging tools, which suggests a read/analysis role. However, the class also includes bookmark() functionality that writes project data to a local file, adding persistent state management not reflected in the documentation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file path is named trend-bookmarks.md, implying Markdown bookmark storage, but bookmark() and listBookmarks() use JSON.parse and JSON.stringify on that same file. This is a direct contradiction between the code's implied documentation/naming and its actual data format.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The bookmark method reads and then writes a file under a fixed workspace path, which is a data-modifying operation. Although the code prints a confirmation after writing, there is no prior disclosure in comments, docstrings, or other user-facing warning that invoking bookmarking will persist data locally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.