ClawHub
Back to skill

Security audit

verify-release

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it reports instructions to change live release distribution during verification, which scanners say may exceed the stated purpose.

Consider whether you trust a skill that may change live release distribution as part of verification, especially if used with publishing credentials. The scanner's assessment is medium confidence and coverage is partial, so some evidence remains incomplete.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Extended-stable verification includes instructions to modify live release distribution state.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The extended-stable checks instruct the agent to repair Docker aliases and promote npm distribution tags, turning a verification request into changes to live release distribution. With publishing credentials, this could cause consumers to receive a release that was not authorized for promotion. The opening verification-only restriction reduces the risk but conflicts with these operational recovery instructions and does not explicitly gate them on separate user authorization.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 51)May include surrounding context.

md
`npmProvenanceAttestationMatched: true`.
3. Plugin publish set:
   - Get exact tag metadata from GitHub, not the local checkout when dirty:
     download `https://api.github.com/repos/openclaw/openclaw/tarball/v<VERSION>`
     into `/tmp/openclaw-v<VERSION>-src`.
   - Derive the full expected npm and ClawHub package sets for the release track
     with the canonical publication planners/collector from the recorded release