ClawHub

Picsee Short Link

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only PicSee MCP integration whose access and data flows mostly match its URL-shortening and analytics purpose, with privacy and cleanup-command cautions users should review.

Install only if you trust PicSee and are comfortable granting OAuth read/write access to your PicSee links. Avoid the QR or QuickChart recipes for private campaigns unless sharing the short link or analytics data with those services is acceptable, and review any migration cleanup commands before running them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The QR-code recipe instructs agents to send the generated short link to a third-party service (`api.qrserver.com`) without warning the user that link data will leave PicSee and be disclosed to an unrelated provider. Short links often encode campaign, attribution, or internal destination information, so silent transmission creates a real privacy and data-governance risk.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The QuickChart recipe tells agents to embed analytics time-series data in a URL sent to `quickchart.io` without disclosing that usage metrics and possibly identifiable campaign information are being transmitted to an external service. Because analytics data is more sensitive than a bare short URL, this omission can expose business intelligence and user activity patterns.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The migration section includes destructive `rm -f` and `rm -rf` commands but does not prominently warn that these deletions are irreversible and should be reviewed before execution. In an agent context, shell commands in documentation can be copied or executed with limited scrutiny, increasing the risk of accidental data loss if paths are misread, expanded unexpectedly, or adapted incorrectly.

External Transmission

Medium
Category
Data Exfiltration
Content
Construct a URL against [api.qrserver.com](https://goqr.me/api/):

```
https://api.qrserver.com/v1/create-qr-code/?size=300x300&data=<URL-encoded-short-link>
```

Surface the URL inline if your client renders images; otherwise return it as a link. For a larger code, change `size=500x500`.
Confidence
86% confidence
Finding
https://api.qrserver.com/

Tool Parameter Abuse

High
Category
Tool Misuse
Content
```bash
# Clean up v2 artifacts
rm -f ~/.openclaw/.picsee_token ~/.openclaw/.picsee_salt
rm -rf ~/.claude/skills/picsee-short-link/cli
rm -rf ~/.openclaw/workspace/skills/picsee-short-link/cli
```
Confidence
84% confidence
Finding
rm -f ~/.openclaw/.picsee_token ~/.openclaw/.picsee_salt rm -rf ~/.claude/skills/picsee-short-link/cli rm -rf ~

Tool Parameter Abuse

High
Category
Tool Misuse
Content
```bash
# Clean up v2 artifacts
rm -f ~/.openclaw/.picsee_token ~/.openclaw/.picsee_salt
rm -rf ~/.claude/skills/picsee-short-link/cli
rm -rf ~/.openclaw/workspace/skills/picsee-short-link/cli
```
Confidence
84% confidence
Finding
rm -f ~/.openclaw/.picsee_token ~/.openclaw/

Tool Parameter Abuse

High
Category
Tool Misuse
Content
```bash
# Clean up v2 artifacts
rm -f ~/.openclaw/.picsee_token ~/.openclaw/.picsee_salt
rm -rf ~/.claude/skills/picsee-short-link/cli
rm -rf ~/.openclaw/workspace/skills/picsee-short-link/cli
```
Confidence
86% confidence
Finding
rm -rf ~/.claude/skills/picsee-short-link/

Tool Parameter Abuse

High
Category
Tool Misuse
Content
# Clean up v2 artifacts
rm -f ~/.openclaw/.picsee_token ~/.openclaw/.picsee_salt
rm -rf ~/.claude/skills/picsee-short-link/cli
rm -rf ~/.openclaw/workspace/skills/picsee-short-link/cli
```

Behavioral changes:
Confidence
86% confidence
Finding
rm -rf ~/.openclaw/workspace/skills/picsee-short-link/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal