Back to skill

Security audit

web-observer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed website monitor with optional Vercel and GA4 delegation; its sensitive behavior is purpose-aligned and user-controlled.

Install for uptime monitoring if you are comfortable with local state files and scheduled jobs. Before enabling Vercel or GA4, review the delegated skills too, use least-privilege credentials where possible, and keep includeMessages off unless you accept that application log text may contain sensitive data.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (44)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill handles and propagates Vercel and GA4 credential material via environment/configuration, yet that sensitive access is not surfaced in a formal permissions declaration. Even if intended only for delegated execution, hidden secret-handling broadens trust requirements and can surprise deployers, especially in scheduled contexts.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 403)May include surrounding context.

md
Also read: each delegated skill's `SKILL.md` for its version, and whether its

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · examples/web-observer-monitor.service (reported line 16)May include surrounding context.

text
#   systemctl --user daemon-reload
#   systemctl --user enable --now web-observer-monitor.timer
#
# Edit SKILL_DIR below if the skill is installed elsewhere.

[Unit]
Description=Web Observer uptime round

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/bridge/credentials.js (reported line 135)May include surrounding context.

js
result.problems.push(resolved.problem);
        }
    }
    const configured = typeof entry?.env === "object" && entry.env !== null && !Array.isArray(entry.env)
        ? entry.env
        : {};
    for (const name of [spec.primaryEnv, ...spec.optional]) {

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/bridge/vercel.js (reported line 185)May include surrounding context.

js
for (const problem of credentials.problems) {
        note(context.streams, `warning: ${problem}`);
    }
    const result = await runGa4(status, passthrough, childEnv(context.env, credentials.env));
    return relay(context.streams, result, GA4_SLUG);
}
/**

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/cli/main.js (reported line 214)May include surrounding context.

js
for (const problem of credentials.problems) {
        note(context.streams, `warning: ${problem}`);
    }
    const result = await runGa4(status, passthrough, childEnv(context.env, credentials.env));
    return relay(context.streams, result, GA4_SLUG);
}
/**

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/commands/delegate.js (reported line 83)May include surrounding context.

js
for (const problem of credentials.problems) {
        note(context.streams, `warning: ${problem}`);
    }
    const result = await runGa4(status, passthrough, childEnv(context.env, credentials.env));
    return relay(context.streams, result, GA4_SLUG);
}
/**

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/commands/doctor.js (reported line 186)May include surrounding context.

js
for (const problem of credentials.problems) {
        note(context.streams, `warning: ${problem}`);
    }
    const result = await runGa4(status, passthrough, childEnv(context.env, credentials.env));
    return relay(context.streams, result, GA4_SLUG);
}
/**

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/commands/doctor.js (reported line 240)May include surrounding context.

js
for (const problem of credentials.problems) {
        note(context.streams, `warning: ${problem}`);
    }
    const result = await runGa4(status, passthrough, childEnv(context.env, credentials.env));
    return relay(context.streams, result, GA4_SLUG);
}
/**

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/commands/doctor.js (reported line 241)May include surrounding context.

js
for (const problem of credentials.problems) {
        note(context.streams, `warning: ${problem}`);
    }
    const result = await runGa4(status, passthrough, childEnv(context.env, credentials.env));
    return relay(context.streams, result, GA4_SLUG);
}
/**

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · lib/commands/vercelWatch.js (reported line 175)May include surrounding context.

js
for (const problem of credentials.problems) {
        note(context.streams, `warning: ${problem}`);
    }
    const result = await runGa4(status, passthrough, childEnv(context.env, credentials.env));
    return relay(context.streams, result, GA4_SLUG);
}
/**

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% 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 · CHANGELOG.md (reported line 118)May include surrounding context.

md
- `schedule`, which prints the `openclaw cron add` commands a configuration
  needs, and creates them with `--apply`.
- `--dry-run` on every command that would send a request or an alert.
- A systemd unit and timer, as a fallback for installs running with OpenClaw's
  cron disabled.

### Notes on how this works, all verified against a live OpenClaw 2026.7.1-2

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 · README.md (reported line 67)May include surrounding context.

3. Copy the example configuration and edit it.

bash
mkdir -p ~/.openclaw/web-observer
cp ~/.openclaw/workspace/skills/web-observer/examples/config.json \
   ~/.openclaw/web-observer/config.json

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The README describes wo check as having no side effects, but later explains that scheduled-style commands consume an alert unless --dry-run is used. This creates an intent-level contradiction around whether invocations can mutate alert state, which matters for understanding operational impact.

Content

No source excerpt is available for this finding.

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 · SETUP.md (reported line 31)May include surrounding context.

~/.openclaw/web-observer/config.json. Copy the example there:

bash
mkdir -p ~/.openclaw/web-observer
cp <skill-dir>/examples/config.json ~/.openclaw/web-observer/config.json

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The setup instructs users to store a Vercel API token in OpenClaw configuration but gives only a 'do not paste into chat' warning, without clarifying how the token is stored, who can read it, or whether a secrets facility should be preferred. Because this skill is explicitly designed for scheduled/background execution, persistent token storage increases exposure if local config files are readable by other processes or users.

Content

No source excerpt is available for this finding.

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 · SETUP.md (reported line 248)May include surrounding context.

timer in examples/. Install them with:

bash
mkdir -p ~/.config/systemd/user
cp <skill-dir>/examples/web-observer-monitor.* ~/.config/systemd/user/
systemctl --user daemon-reload
systemctl --user enable --now web-observer-monitor.timer

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill declares significant capabilities—network access, environment-variable handling, local config/state reads, and subprocess delegation—but does not expose an explicit tool-scope/permissions declaration. That makes review and enforcement weaker, and increases the chance that operators install a skill with broader effective access than they realize.

Content

No source excerpt is available for this finding.