What it does
This entry points to a single SKILL.md file from the mukul975 Anthropic Cybersecurity Skills library, a community project not affiliated with Anthropic PBC. Based on its file path, the skill concerns hunting for scheduled task persistence. The library's skills follow the agentskills.io open standard.
An analyst or an AI agent might reach for this skill when investigating whether an attacker has set up persistence through scheduled tasks. The wider library holds 818 skills across 34 security domains, and the publisher states that each skill is mapped to the frameworks relevant to its type, such as MITRE ATT&CK and NIST CSF 2.0.
To use it, clone the repository and point an AI agent at the skills folder. The publisher lists compatibility with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI and other agentskills.io-compatible platforms.
Limitations and requirements
The publisher states that the library includes offensive and dual-use techniques intended for authorised penetration testing, security research, defence and education. Use them only against systems you own or have explicit written permission to test, and comply with applicable laws and rules of engagement. The user is solely responsible for how the skills are used. The project is community-created and not affiliated with Anthropic PBC.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
Sources
- AgentSkillsDir first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source
Review source
As shown on agentskillsdir.com when we last read it