ClawHub
Back to skill

Security audit

PowPow Simple — 发游记上地图，创建会聊天的数字人

Security checks for vulnerabilities and agentic risk

Overview

The skill’s publishing, account use, and public-map sharing fit its stated purpose and require explicit user confirmation.

Review the separate powpow-cli package before installing it, since it performs login and network operations. Enter your password only in your own terminal. Confirm the account, photos, text, and public location before publishing; omit location if you do not want a map pin. Digital-human creation spends two non-refundable badges and expires after 30 days. Request a translation if you cannot read the Chinese preview.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/security.md (reported line 40)May include surrounding context.

md
- `POST /api/upload/post-image` — local image upload (multipart `file`; login required)
- `POST /api/posts` — create post (login required; server enforces limits & moderation)
- `GET  /api/posts/{id}` — verify a post
- `DELETE /api/posts/{id}` — delete own post (test cleanup)
- `POST /api/digital-humans` — create a digital human (login required;
  consumes 2 badges, expires after 30 days)
- `POST /api/digital-humans/generate-avatar` — AI avatar from the persona

The workflow fixes the user-facing preview language to Chinese without user opt-in.

Low
Category
Output Handling
Confidence
97% confidence
Finding

Line 283 specifies a Chinese-language preview, and line 295 requires presenting that preview before publication. Although line 201 respects the user's language preference for post content, the preview has no equivalent language choice or documented justification for being Chinese-only.

Content

No source excerpt is available for this finding.