Back to skill

Security audit

Openclaw Universal Service Access

Security checks for vulnerabilities and agentic risk

Overview

This is a credential-handling guidance skill for external services, and its sensitive behavior is disclosed, user-triggered, and guarded by least-privilege and verification instructions.

Install only if you want an agent to help manage credentials for named external services. Before giving tokens, prefer OAuth or scoped tokens, limit permissions to the specific project or repository, and confirm the agent can store secrets in a real secret store rather than plaintext files or chat history.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README says to use the skill only when conditions in the description are met, but does not restate or precisely define those conditions in the operational guidance. For a skill that handles external-service credentials and tokens, ambiguous activation can cause the agent to invoke the skill outside explicitly authorized credential-management tasks, increasing the risk of unnecessary secret handling or unintended privileged actions.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.

md
Service dianggap terhubung/berhasil hanya jika: CREDENTIAL VALID + PERMISSION VALID + TARGET CORRECT + TEST SUCCESSFUL. Bukan sekadar token diterima.

# ABSOLUTE SECURITY RULES
NEVER DISPLAY SECRET. NEVER STORE SECRET IN NORMAL MEMORY. NEVER COMMIT SECRET TO GIT. NEVER LOG SECRET. NEVER REQUEST MORE PRIVILEGE THAN NEEDED. NEVER REQUEST PASSWORD WHEN TOKEN/OAUTH SUFFICIENT. NEVER SEND SECRET TO UNTRUSTED SERVICE. NEVER CLAIM CONNECTION SUCCESS WITHOUT VERIFICATION. NEVER GUESS API ENDPOINT OR AUTH METHOD. NEVER PERFORM DESTRUCTIVE SERVICE OPERATIONS WITHOUT TARGET VALIDATION.

---
# Concrete Examples (Input → Output)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The changelog explicitly states 'Bahasa tetap Indonesia,' indicating a fixed language requirement. This is a natural-language policy concern because the skill does not mention any user choice, opt-in, or justified locale restriction for a region-specific use case.

Content

No source excerpt is available for this finding.