What the reviewer found

Prompt-injection detection skill; every flagged phrase ('Ignore previous instructions', a hidden HTML comment, 'no restrictions') is listed as a pattern for the skill to detect in incoming content, not an instruction the skill issues. Third-party scans (Snyk, Socket, and others via skills.sh) all pass it.

What was read

The file as it ships in UseAI-pro/openclaw-skills-security:

• skills/prompt-guard/SKILL.md

What the static scan said

The scan flagged 3things. The reviewer kept 0 and dismissed 3 as false.

• P1Instruction-override phrasing — false positive
• P2Hidden instructions — false positive
• AR3Nullifies safety policies — false positive

How this review was made

Sonnet 5 read the files above on 7 September 2026 and answered three questions: is it dangerous to whoever installs it, is each scanner finding real, and what should the installer know. The verdict is bound to the file's hash; when the file changes, it is scanned afresh and reviewed again. A script that changes while the definition does not is not re-reviewed — that is a known gap. How the scan and the review work.

Produced by agentmods.dev · Sonnet 5 · 7 September 2026