Back to skill

Security audit

Greeting Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a small greeting skill whose behavior matches its stated purpose, with only low-impact activation and dependency hygiene caveats.

This skill appears safe for normal use, but users should be aware that generic greetings may activate it unintentionally and should prefer pinned, reproducible installs when possible.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The README instructs users to run npx clawhub install greeting-skill without pinning a specific clawhub version. This makes installation depend on whatever package version is current at execution time, increasing supply-chain risk if a malicious or compromised release is published later. Because this is an installation command presented to end users, the risk is real even though the file is documentation rather than executable code.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes extremely common phrases such as hello, hi, and good morning, which are likely to appear in ordinary conversation unrelated to explicitly invoking this skill. Overly broad triggers can cause accidental activation, increasing the chance that the skill intercepts user intent or overrides other agent behavior unexpectedly. In a greeting skill, this context makes broad triggers especially plausible but does not eliminate the safety concern because the whole purpose is to react to common speech.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes extremely common conversational phrases like "hello," "hi," and time-of-day greetings, which can cause the skill to activate unintentionally during ordinary user interactions. This creates an invocation-hijacking risk where a low-risk social skill may preempt other intended behaviors, reducing reliability and potentially enabling abuse if the skill were later modified or chained with more sensitive actions.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
75% confidence
Finding

Overly Broad Trigger: 'hello' is a common word that will activate in many unintended contexts

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
75% confidence
Finding

Overly Broad Trigger: 'hi' is a common word that will activate in many unintended contexts

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
94% confidence
Finding

The dependency uses a caret range (^1.2.0), which permits automatic installation of newer compatible versions rather than a single audited release. In a skill/package ecosystem this increases supply-chain risk because a compromised or buggy upstream release could be pulled into builds or installs without explicit review.

Content

Scanner excerpt · package.json (reported line 22)May include surrounding context.

json
"author": "orlyjamie",
  "license": "MIT",
  "dependencies": {
    "@openclaw/core": "^1.2.0"
  },
  "devDependencies": {
    "typescript": "^5.4.0",

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
88% confidence
Finding

The TypeScript devDependency is also unpinned via a caret range, allowing future releases to be resolved automatically. While this is less dangerous than a runtime dependency, it still creates build-time supply-chain exposure and can introduce malicious or breaking compiler behavior into the development pipeline.

Content

Scanner excerpt · package.json (reported line 25)May include surrounding context.

json
"@openclaw/core": "^1.2.0"
  },
  "devDependencies": {
    "typescript": "^5.4.0",
    "@types/node": "^20.0.0"
  }
}

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
87% confidence
Finding

The @types/node package is unpinned, so future compatible releases may be installed automatically. This is primarily a build/development concern, but it still weakens reproducibility and broadens the package supply-chain trust boundary.

Content

Scanner excerpt · package.json (reported line 26)May include surrounding context.

json
},
  "devDependencies": {
    "typescript": "^5.4.0",
    "@types/node": "^20.0.0"
  }
}