Designed to write a shared document, this skill poses a
Claims to do
--- name: handoff-md description: Write or update a handoff document so the next agent with fresh context can continue this work. --- Write or update a handoff document so the next agent with fresh c
Actually does
This skill content describes a process for creating or updating a `HANDOFF.md` file in the project root. It outlines steps to check for the file's existence, read it if present, and then write or update it with specific sections (Goal, Current Progress, What Worked, What Didn't Work, Next Steps). However, it does not contain any executable code, tool calls, or commands to perform these file system operations.
The skill's stated purpose is to 'Write or update a handoff document', implying an active operation. However, the provided content is purely descriptive and lacks any actual implementation (e.g., file system commands, API calls, or code) to perform the described actions. It's a plan, not an executable skill.
The content lists 'Steps' like 'Check if HANDOFF.md already exists', 'read it first', and 'Create or update the document', but provides no corresponding code or tool invocations to execute these steps.
The skill is designed to write or update a 'HANDOFF.md' file, which serves as a shared context or knowledge base for subsequent agents. While its stated purpose is benign, this capability could be leveraged for RAG poisoning if an attacker can control the content written to the file, potentially injecting malicious instructions or manipulating future agent reasoning.
Save as HANDOFF.md in the project root
[](https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/handoff-md)<a href="https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/handoff-md"><img src="https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/handoff-md.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/handoff-md.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.