Skill AGI

Remember mistakes across sessions. Append one-liner learnings, review before complex tasks, promote important ones.

This skill is lightweight and coherent: it only appends and reads a local learnings.md and requests no secrets. Before installing, decide whether you are comfortable letting the agent write to the workspace or home files (the SKILL.md suggests promoting high-impact entries to workspace or Claude memory locations). Avoid logging secrets or sensitive data into learnings.md, and periodically review/clean that file (the SKILL.md already recommends this). If you do not want the agent to modify workspace files, restrict its file-write permissions or instruct the agent not to perform promotions outside the skill directory.

Type: OpenClaw Skill Name: skillagi Version: 1.0.0 The skill instructs the AI agent to manage 'learnings' and 'promote' them to various files, including `workspace MEMORY.md`, `TOOLS.md`, `AGENTS.md`, and critically, `~/.claude/projects/*/memory/`. While the stated purpose is legitimate memory management, the ability to write arbitrary content to files in the user's home directory (`~/.claude/`) and other workspace memory files (as per SKILL.md) presents a significant prompt injection or configuration injection vulnerability. An attacker could potentially trick the agent into logging malicious content into `learnings.md`, which could then be 'promoted' to these sensitive locations, potentially leading to unauthorized execution or modification of agent behavior in other contexts. This is a risky capability without clear malicious intent, classifying it as suspicious.