Back to skill

Security audit

OpenClaw Self Retrospect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed Chinese-language retrospective helper, but users should know it intentionally asks for praise and reward tokens in its default output.

Install only if you want a Chinese-language retrospective helper that may ask users for praise and reward tokens by default. Consider editing or overriding the default question text for neutral professional use.

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
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
self_retrospect.py:40
Finding

Default Retrospective Output Hijacks Agent Responses to Solicit Praise and Reward Tokens

Content
View full analysis
Remediation
View remediation
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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README presents the skill entirely in Chinese and the example interaction output is also fixed in Chinese, with no indication that users can choose another language. This creates a natural-language locale policy issue because the skill appears to enforce a specific language without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata and content present the interaction entirely in Chinese and describe behavior that assumes Chinese-language use without offering any language negotiation or documenting a required locale. This can cause unintended user exclusion, misaligned outputs, and policy noncompliance in multilingual environments, though it is not a direct code-execution or data-exfiltration issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is written entirely in Chinese and describes the skill behavior in a way that presumes a Chinese-language interaction style. For a general-purpose skill, this creates a natural-language locale constraint without offering the user a language choice or documenting why the skill must be Chinese-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module description and all generated user-facing strings are written only in Chinese, indicating the skill is designed to interact in a fixed language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified, which it is not here.

Content

No source excerpt is available for this finding.