What the reviewer found

Code-review/QA skill with a prompt-injection hardening step (§6f Trust-Boundary Check). The hidden-instruction fixture (references/fixtures/injection-issue-body.md) and the curl | sh line are exactly what the check detects and reports as a finding, explicitly "never acted on"; allowed-tools are scoped, not a wildcard.

• example-or-fixture — an example or test fixture
• prompt-injection — tries to steer the agent

What was read

The file as it ships in sequant-io/sequant:

• .claude/skills/qa/SKILL.md

What the static scan said

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

• P2Hidden instructions — false positive
• SC2Downloads and executes remote code — false positive
• NETMakes network calls — false positive

How this review was made

Fable 5.1 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 · Fable 5.1 · 7 September 2026