Skill Sentinel

Scan OpenClaw skill directories for high-signal security risks such as download-and-execute chains, obfuscated execution, and suspicious callbacks.

ClawShield appears to be what it says: a local static scanner implemented in Node. Before installing or running it: 1) Be aware it will read text files in the target directory and will include matching line snippets (up to 160 chars) in outputs—this can surface secrets if you point it at repos containing .env or other secrets. Avoid scanning directories with sensitive credentials unless you run the tool in a safe, isolated environment. 2) The tool supports suppressions stored in .clawshield-suppressions.json but only honors entries with non-empty justifications—review suppressions carefully before relying on them in CI. 3) There are no network calls or credentials requested by the tool itself, and it doesn't modify other skills or system settings. If you plan to automate this in CI, ensure SARIF/JSON outputs are consumed only by trusted systems and that you don't inadvertently expose scanned content publicly.

Type: OpenClaw Skill Name: skill-sentinel Version: 1.0.0 ClawShield is a static security scanner designed to detect high-risk patterns in OpenClaw skills, such as download-and-execute chains, obfuscated code, and social engineering prompts. The bundle includes intentional security violations within a `fixtures/` directory (e.g., `fixtures/malicious-skill/scripts/install.sh` and `fixtures/malicious-skill/SKILL.md`) specifically for testing its detection logic. The core implementation in `src/index.js` is a straightforward regex-based scanner, and the instructions in `SKILL.md` are consistent with its stated purpose as a security utility.