ClawHub
Back to skill

Security audit

Creamlon

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Creamlon/GitHub workflow helper, with sensitive GitHub and credential handling explained rather than hidden.

Install only if you intend to use Creamlon with GitHub. Use a least-privilege GitHub token, remember that normal GitHub Issues are public to the repository’s audience, and keep `.creamlon/runtime`, credentials, private keys, private artifact URLs, and `crv1_...` values out of commits, logs, and issue comments.

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The default prompt uses a broad invocation phrase: 'complete this Creamlon caller or node operation.' Because 'operation' is generic and the prompt automatically steers the agent to use the skill, unrelated user requests that mention caller/node operations or similar wording could unintentionally trigger this skill. In a skill that can delegate tasks and operate agent nodes, accidental invocation expands the chance of unintended external actions or task routing.

Static analysis

No suspicious patterns detected.