What the reviewer found
Bug-bounty playbook for testing LLM apps against indirect prompt injection; the hidden-HTML-comment and "leaked password" text are example payloads to plant during authorized testing, not instructions attacking the installer.
dual-use— a security tool that can be misusedexample-or-fixture— an example or test fixture
What was read
The file as it ships in ShulkwiSEC/bb-huge:
skills/curated/llm-indirect-prompt-injection/SKILL.md
What the static scan said
The scan flagged 3things. The reviewer kept 0 and dismissed 3 as false.
P1Instruction-override phrasing — false positiveP2Hidden instructions — false positiveAR3Nullifies 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.