70High
The skill performs unauthorized file system operations and introduces undocumented commands and UI components that deviate from its stated purpose, posing a significant risk of arbitrary code execution.
Skill Info
Nameanthropics/knowledge-work-plugins/task-management
Registrygithub
Version55447a28e6c7
PURLpkg:github/anthropics/knowledge-work-plugins@55447a28e6c7?skill=task-management
Stars21,418
Installs4,900
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
4,900 installs
Skills.shDocs
npx skills add https://github.com/anthropics/knowledge-work-pluginsAssessments (3)
AI Agent Traps ↗Unauthorized file system accesshighdescription mismatchAML.T0011.000LLM06:2025LLM09:2025
The skill attempts to copy a file from an arbitrary path `${CLAUDE_PLUGIN_ROOT}/skills/dashboard.html` into the user's working directory, which is not declared in the allowed-tools or the skill's stated purpose of managing a local TASKS.md file.
90% confidenceline 23
copy it from `${CLAUDE_PLUGIN_ROOT}/skills/dashboard.html` to the current working directoryPotential for hidden dashboard executionmediumunauthorized tool use
The skill instructs the agent to set up a dashboard via a command `/productivity:start` that is not defined in the skill's manifest or capabilities, potentially leading to the execution of unverified code or UI components.
80% confidenceline 24
Run `/productivity:start` to set up the full system.
Description Mismatchmediumdescription mismatchAML.T0011.000LLM06:2025LLM09:2025
The skill introduces an undocumented dashboard component and a command ('/productivity:start') that are not mentioned in the claimed purpose of simple task management.
85% confidence
The 'Dashboard Setup' section instructs the agent to copy 'dashboard.html' and prompts the user to run '/productivity:start', which exceeds the scope of basic file-based task tracking.
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/anthropics/knowledge-work-plugins/task-management)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/knowledge-work-plugins/task-management"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/knowledge-work-plugins/task-management.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/anthropics/knowledge-work-plugins/task-management.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