Back to skill

Security audit

DiePre Embodied Bridge

Security checks for vulnerabilities and agentic risk

Overview

The skill is documentation-only and purpose-aligned, but it describes automatic persistent tuning of robot action parameters without clear safety bounds or operator approval.

Review this carefully before installing in any robotics workflow. Treat the self-evolution feature as experimental unless the implementation adds strict schema validation, trusted log writers, immutable safety limits, simulation or operator approval before activation, rollback, and clear data retention rules.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:100
Finding

Unvalidated Persistent Adaptation of Robot-Control Parameters

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file’s operational instructions and task descriptions are presented entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy requirements when a skill implicitly forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README explicitly advertises automatic execution logging, failure-pattern extraction, and self-tuning, but provides no safeguards around what data is logged, how long it is retained, or how optimization changes are bounded and reviewed. In a robotics/vision-action bridge, these behaviors can capture sensitive operational data and can also introduce unsafe or unreviewed behavior changes that affect downstream motion planning.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing procedural instructions only in Chinese, which can violate language/locale policy when no user opt-in or region-specific justification is provided. The policy explicitly flags forced language constraints across all file types, and this file does not mention any alternative language support or rationale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill description and operational content are presented in Chinese, but the file does not indicate that the skill is region-specific or offer an alternative language/locale option. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.