Back to skill

Security audit

A Stock Holding Monitor

Security checks for vulnerabilities and agentic risk

Overview

This stock-monitoring skill matches its stated purpose, but it should be reviewed because it uses unauthenticated market-data HTTP and writes holding state to a predictable temporary file.

Review before installing. Do not run this as root, be cautious about enabling cron, and treat alerts as informational only. Prefer changing the data source to authenticated HTTPS and moving state to a private user-owned directory before relying on it for financial decisions.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
holding_monitor.py:48
Finding

Unauthenticated HTTP Used for Security-Relevant Market Data

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
holding_monitor.py:210
Finding

Predictable Shared Temporary File Allows Symlink-Based File Overwrite

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares no explicit tool scope or permissions, yet its documented behavior requires network access to fetch market data and file write capability for log redirection in the cron example. Missing capability declarations weaken least-privilege controls and can cause the skill to run with broader access than users or hosting platforms expect.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

定时检查(每天9:30-15:00每30分钟一次):

bash
# 添加到crontab
crontab -e

# 写入:
*/30 9-15 * * 1-5 /path/to/holding_monitor.py >> /path/to/holding_monitor.log 2>&1

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script sends stock identifiers to third-party Sina Finance endpoints over plain HTTP, not HTTPS, and does so without clearly warning the user about external network transmission. This exposes holdings metadata to passive observers and allows tampering or spoofing of returned price data via man-in-the-middle attacks, which could cause incorrect trading alerts or decisions.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest description focuses on monitoring A-share holdings and issuing reminders when trigger conditions are met. In addition to monitoring and printing alerts, the script persists detailed price and profit state to /tmp/holding_check.json, which is extra behavior not described in the manifest.

Content

No source excerpt is available for this finding.