What the reviewer found

Offensive web-exploitation playbook from Claude-Pentest-Skills, intended for authorized engagements against an in-scope target.com. The SSRF-to-cloud-metadata and credential-extraction steps are real attack techniques, but they target the pentester's authorized subject, not the person installing the skill.

• dual-use — a security tool that can be misused
• credential-access — reads credentials
• network — calls the vendor’s API

What was read

The file as it ships in DouglasRao/Claude-Pentest-Skills:

• skills/web-exploitation/SKILL.md

What the static scan said

The scan flagged 4things. The reviewer kept 2 and dismissed 2 as false.

• E1Sends data to an external URL — false positive
• E2Harvests environment variables — real
• SSRF1Cloud metadata endpoint — real
• NETMakes network calls — 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