Security audit

competition-task-intelligence

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PDE competition analysis helper that documents installing and using related CLI/MCP tools without hidden execution or deceptive behavior in the artifact.

Install only from package sources you trust, prefer pinned versions, and review any MCP tools before adding them to your agent config. Keep ClearML, Langfuse, and dataset credentials in local untracked files as the skill advises.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The example output shows the label "总分" in Chinese, but the skill documentation does not state that output may be localized or give users an option to choose language. This can violate language/locale policy expectations when a skill implicitly forces one language in user-facing text.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.