4 skills · sorted by relevance
Living catalogue of 7 known hazard entries (SE-01 through SE-07) specific to agent-studio: Windows backslash paths, prototype pollution, hook exit codes, async swallowing, ReDoS in glob-to-regex, DST arithmetic, array mutation during iteration. Each entry: symptom, root cause, fix, test assertion.
The English summary is being prepared. Showing the original description.
Reviews APIs and configuration designs for choices that make security mistakes easy. Checks unsafe defaults, confusing parameter types, and hidden failures, then validates whether misuse creates a real vulnerability and assigns severity.
Identify error-prone APIs, dangerous configuration, and footgun designs that enable security mistakes. Use for API ergonomics, misuse resistance, secure defaults, or pit-of-success reviews; use code-review for general defects.
The English summary is being prepared. Showing the original description.
Identify dangerous API footguns, surprising default behaviors, and sharp edges in codebases and dependencies. Adapted from Trail of Bits. Use during code review to catch APIs that are easy to misuse, configurations that surprise, and abstractions that leak.
The English summary is being prepared. Showing the original description.