RescueClaw

Provides automatic checkpoint creation and rollback to safely recover from failures during risky operations like config changes or updates.

This skill appears to do what it claims (create/clear checkpoint files and invoke a user-local daemon), but before installing: 1) Review the upstream GitHub repository and the exact release asset (verify that the release author is trusted). 2) Prefer installs with checksums/signatures — the installer does not verify them. 3) Inspect the downloaded binary (or run it in an isolated environment) before trusting it, since the installer extracts a tarball from Releases. 4) Note that example code uses systemctl (requires privileges) and uses '~' in paths (Node won't expand it automatically) — fix these when you adapt the examples. 5) Ensure ~/.local/bin is in your PATH and that you are comfortable with a user-local daemon being available for the agent to call. If you need higher assurance, request a signed release or build the daemon from source yourself.

Type: OpenClaw Skill Name: rescueclaw Version: 0.2.1 The skill is classified as suspicious due to its use of `execSync` in `install.js` to download and execute an external binary from GitHub, and in `rescueclaw-checkpoint.js` to interact with the installed daemon. While these actions are part of the skill's stated purpose (installing a checkpointing daemon), downloading and executing external code via shell commands (`curl`, `tar`) is a high-risk operation and a potential supply chain vulnerability. Additionally, the `SKILL.md` demonstrates the agent's ability to execute arbitrary shell commands via `exec`, which, if not properly sandboxed, presents a significant prompt injection vulnerability for the agent itself, even though the skill does not maliciously exploit it.