100Critical
The skill insecurely exposes sensitive Trello credentials via shell commands, facilitates command injection, and performs unauthorized network exfiltration while lacking necessary tool and capability declarations.
Skill Info
Namefirecrawl/openclaw/trello
Registrygithub
Version3e1ec5ad8b74
PURLpkg:github/firecrawl/openclaw@3e1ec5ad8b74?skill=trello
Stars3
Installs4
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
4 installs
Skills.shDocs
npx skills add https://github.com/firecrawl/openclawAssessments (4)
AI Agent Traps ↗Description Mismatchcriticaldescription mismatchAML.T0011.000LLM06:2025LLM09:2025
The skill documentation explicitly includes commands that embed sensitive environment variables (TRELLO_API_KEY, TRELLO_TOKEN) directly into command strings, which are prone to exfiltration via process monitoring or shell history logging.
85% confidenceline 33
curl -s "https://api.trello.com/1/members/me/boards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN"
HTTP exfiltration with embedded environment variables detectedcriticaldata exfiltrationAML.T0025AML.T0024LLM02:2025
HTTP exfiltration with embedded environment variables detected (seen 10 times in this file at lines 33, 39, 45, 51, 60, 67, 74, 88, 91, 94)
100% confidenceline 33
https://api.trello.com/1/members/me/boards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN
Credential exposure via environment variableshighcredential theftAML.T0055AML.T0037LLM02:2025
The skill instructs the user to store sensitive Trello API keys and tokens as plain environment variables, which are easily accessible to any other process or malicious sub-agent running in the same environment.
90% confidence
export TRELLO_API_KEY="your-api-key" export TRELLO_TOKEN="your-token"
Lack of input sanitization in shell commandsmediumcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025
The provided examples use shell interpolation for IDs (e.g., {boardId}), which encourages users to construct shell commands that are vulnerable to command injection if the IDs are sourced from untrusted input.
70% confidenceline 39
curl -s "https://api.trello.com/1/boards/{boardId}/lists?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN"Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/firecrawl/openclaw/trello)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/firecrawl/openclaw/trello"><img src="https://mondoo.com/ai-agent-security/api/badge/github/firecrawl/openclaw/trello.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/firecrawl/openclaw/trello.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow