Tiktok To Mealie

• Outcome: Review
• Latest audit: Sep 12, 2026 · 3:03 AM UTC
• Version: 1.2.0

Overview

This skill has a coherent recipe-import purpose, but it can automatically write to Mealie from untrusted TikTok content without enough scoping or fetch-safety guidance.

Review before installing. Use a limited Mealie API token if possible, keep the token protected, and avoid giving it broad agent permissions. The skill should ideally add explicit confirmation before writes from ambiguous TikTok links, treat TikTok text only as untrusted recipe data, and validate redirects and image downloads before import.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

• Location: SKILL.md:38

Finding

Untrusted TikTok content is processed without prompt-injection boundaries

Content

View full analysis

Remediation

View remediation

T09 · Insecure Skill Coding Practices

Warning

• Location: references/workflow.md:38

Finding

Redirect and image-fetch instructions omit SSRF and resource-validation controls

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Rogue Agent: Self-Modification, Session Persistence
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

This markdown file states that the skill imports results into Mealie and uploads a cover image, both of which can create or modify user data in an external system. The description does not include any user-facing warning about these write operations or their effect on the user's recipe library.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The skill explicitly performs state-changing actions in Mealie (creating recipes and uploading images) but does not clearly require explicit user confirmation at the point of modification or prominently warn that it will write to the user's Mealie instance. In an agent setting, this can lead to unintended data changes from ambiguous inputs such as a bare TikTok link, causing surprise writes, clutter, or incorrect recipe imports.

Content

No source excerpt is available for this finding.

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/configuration.md (reported line 26)May include surrounding context.

Example:

bash

mkdir -p ~/.openclaw/secrets
printf '%s\n' 'https://mealie.example.com' > ~/.openclaw/secrets/mealie_base_url
printf '%s\n' 'your_token_here' > ~/.openclaw/secrets/mealie_token
chmod 600 ~/.openclaw/secrets/mealie_*

Sudo/Root Execution

Medium

• Category: Privilege Escalation
• Confidence: 80% confidence

Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/configuration.md (reported line 29)May include surrounding context.

mkdir -p ~/.openclaw/secrets printf '%s\n' 'https://mealie.example.com' > ~/.openclaw/secrets/mealie_base_url printf '%s\n' 'your_token_here' > ~/.openclaw/secrets/mealie_token chmod 600 ~/.openclaw/secrets/mealie_*

text

## Resolution order

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 81% confidence

Finding

The skill documentation says it requires a Mealie API token and suggests storing it in environment variables or local secret files. However, it does not include any warning or guidance that the skill will use this credential to access the user's Mealie account or that the token should be protected.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.