yf-memo

Personal memo and todo management system. Use when user expresses intent related to remembering, tracking, or managing tasks.

This skill appears to be what it claims (a local memo/todo system) but has several implementation issues you should review before installing: 1) The hook and some docs reference template filenames (template-todo.md, template-done.md, assets names) that don't match the provided asset filenames (template-pending.md, template-completed.md) — running the hook as-is may fail or behave unexpectedly. 2) Several scripts and examples use sed -i '' (BSD/macOS syntax) which will break on many Linux systems; expect portability bugs. 3) The skill suggests editing ~/.bashrc, creating symlinks in ~/.local/bin, and adding cron jobs — these change your environment and should only be performed with your explicit consent after reading the hook/install commands. 4) The documentation contains both a directive to avoid hard-coded phrase-action mappings and an implementation doc that lists many exact regex patterns, which is an internal inconsistency (affects how the assistant may parse user text). Recommended actions: review the hook and scripts line-by-line (especially any cp, sed, or echo >> ~/.bashrc operations); run in a controlled environment (or sandbox) first; backup ~/.openclaw/workspace files before running hooks; and request corrected hook/assets from the author (or fix template names and sed compatibility) before enabling automatic setup or cron tasks.

Type: OpenClaw Skill Name: yf-memo Version: 1.0.0 The skill implements a functional personal memo system but contains significant shell injection vulnerabilities. The `memo-helper.sh` script uses unsanitized user input directly within `sed` commands and shell arguments, which could be exploited to execute arbitrary commands if a user provides a crafted task description (e.g., containing backticks or semicolons). While the behavior appears aligned with the stated purpose of task management and no clear evidence of intentional malice or data exfiltration was found, the high-risk execution patterns in `SKILL.md` and `implementation.md` warrant a suspicious classification.