Security audit

cogvideox 生成视频

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims, but it logs full prompts, returns raw provider details, and can poll the video API forever.

Review this before installing if prompts may contain private or confidential content, or if API quota/cost control matters. The skill should ideally avoid logging full prompts, return only sanitized status and video URL fields, and add bounded polling with timeout handling.

A.I.G

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 (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/generate_video.py:41
Finding: Unbounded video-status polling can exhaust service resources
Content: View full analysis
Remediation: View remediation
= deadline: return { "status": "timeout", "message": "Video generation did not complete within the allowed time." } result = client.videos.retrieve_videos_result(id=task_id) status = getattr(result, "task_status", None) if status == "SUCCESS": return { "status": "success", "message": "Video generation completed.", "video_url": result.video_url, } if status == "FAILED": return { "status": "failed", "message": "Video generation failed." } if status not in {"PENDING", "PROCESSING", "RUNNING"}: return { "status": "failed", "message": "The provider returned an unexpected task status." } time.sleep(min(5 * (2 ** min(attempt, 3)), 30)) ``` ]]>

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/generate_video.py:28
Finding: Sensitive prompts and backend diagnostics are exposed through logs and responses
Content: View full analysis
Remediation: View remediation

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 (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The natural-language content in the description and usage instructions is entirely Chinese, which can impose a specific language on users without opt-in. The policy for this audit flags language or locale constraints unless the skill explicitly offers a choice or clearly justifies the restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This file’s natural-language docstring, error messages, progress prints, and skill metadata descriptions are all presented only in Chinese, with no indication that the user can choose another language. That can violate a language/locale policy when skills are expected to respect user language preference or provide opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.