Back to skill

Security audit

Changelog Watcher

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed release-monitoring helper that queries GitHub and npm and keeps local state, with minor scope and persistence caveats but no artifact-backed malicious behavior.

Install only if you are comfortable with the skill sending your configured repository and package names to GitHub and npm, storing last-seen versions locally, and optionally being scheduled by you. Use the dry-run command when you do not want state.json advanced, and treat fetched release notes as untrusted external content.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The declared behavior promises npm support, changelog summarization, breaking-change detection, monitoring, and scheduling, but the analyzed implementation reportedly lacks much of that functionality. This mismatch can mislead users and higher-level agent routing into invoking the skill in situations where it cannot safely or accurately perform the requested task, which is a trust and integrity problem.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill instructs use of shell commands, local file reads/writes, and networked scripts, but it does not declare any explicit tool scope or permissions boundary. In an agent environment, that increases the chance the skill is invoked with broader capabilities than users expect, enabling unintended filesystem changes and outbound requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match common requests like checking updates or asking what's new, which can cause over-invocation of a skill that performs shell, network, and file operations. In agent systems, unnecessary invocation expands attack surface and may lead to unintended local state changes or external requests without a sufficiently precise user intent match.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
89% confidence
Finding

The skill maintains persistent state in state.json and user configuration in watchlist.json across sessions. While this is functional rather than overtly malicious, session persistence can retain sensitive project interests or silently influence later runs, making the behavior security-relevant if not clearly disclosed and consented to.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
## Files

- `watchlist.json` — user config (create from `assets/watchlist.example.json`)
- `state.json` — auto-managed last-seen versions (do not edit)
- `scripts/compare_versions.py` — main entry point; calls the others
- `scripts/check_github.py` — GitHub releases API

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% 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 · references/setup-guide.md (reported line 18)May include surrounding context.

│ └── setup-guide.md ← you are here ├── assets/ │ └── watchlist.example.json ├── watchlist.json ← create this (user config) └── state.json ← auto-created on first run

text

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/check_github.py (reported line 23)May include surrounding context.

python
def fetch_releases(owner: str, repo: str, limit: int = DEFAULT_LIMIT) -> list:
    url = f"https://api.github.com/repos/{owner}/{repo}/releases?per_page={limit}"
    req = urllib.request.Request(
        url,
        headers={

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/compare_versions.py (reported line 54)May include surrounding context.

python
script_path = os.path.join(SCRIPT_DIR, script_name)
    cmd = [sys.executable, script_path] + list(args)
    try:
        result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
        if result.returncode == 2:
            print(f"[warn] Rate limited while running {script_name}. Skipping.", file=sys.stderr)
            return None

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill directs creation of watchlist.json and automatic updates to state.json but does not prominently warn that local files will be created or modified. That omission can cause unexpected persistence or configuration changes on the user's machine, especially when the skill is auto-invoked by an agent.

Content

No source excerpt is available for this finding.