Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
Agent reference creator
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent Russian-language OpenClaw reference-document generator with disclosed local file writes and no evidence of exfiltration, privilege escalation, or hidden execution.
Install this only if you want a Russian-language workflow for creating OpenClaw specialization references. Review the generated reference path and content before saving, especially when a specialization name could collide with an existing file.
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
- 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 (7)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The natural-language content consistently forces a specific language for the skill documentation and usage instructions. The policy for SQP-3 flags language or locale constraints when they are imposed without user opt-in or an explicit, justified regional scope.
- Content
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The required frontmatter explicitly fixes
lang: ru, which imposes a single language/locale for generated reference files. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly justified as region-specific, which is not stated here.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The file template repeats the fixed setting
lang: ru, reinforcing a mandatory Russian-only output format. Because the skill otherwise describes general reference creation rather than a clearly region-scoped tool, this appears to force a locale without user opt-in.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
This shell script contains user-facing comments, status messages, errors, and confirmation prompts exclusively in Russian. Because the file does not provide any language selection, fallback, or justification for being Russian-only, it violates the natural-language policy requirement against forcing a specific language without user opt-in.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This markdown file explains that the skill creates output files at a specific path, which affects user/project data. Under the markdown criteria for SQP-2, descriptions should include warnings when behavior can modify stored data, but no caution or disclosure is provided here.
- Content
Static analysis
No suspicious patterns detected.