ClawHub
Back to skill

Security audit

Collab Ingest Demo

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only demo for packaging and publishing a ClawHub skill, with no hidden execution or persistence.

Before installing or reusing this skill, treat the non-dry-run `clawhub publish` line as a real remote publish operation. Run the dry-run first, confirm the authenticated account and unique slug, and only run the final publish command when you intend to upload the asset.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill includes a concrete non-dry-run `clawhub publish` command that performs a real remote upload, immediately adjacent to a dry-run example, but without an explicit warning that the second command has side effects. In a skill meant to be reproduced by users or agents, this can lead to unintended publication of assets, metadata leakage, or accidental modification of remote state if the command is copied verbatim.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The description field is entirely in Chinese, which can impose a specific language on users or downstream tooling without opt-in. The file does not indicate that the skill is region-specific or provide an alternative language option.

Static analysis

No suspicious patterns detected.