Standard
Reference list of top LLM application security risks used as a mapping target by several of the compared tools.
Lianxi, an independent project, proposes that a company agent behind Meta and Sierra's PAP hold no credentials and act only through single-use grants. Its authors say the worst case becomes whatever policy allows. The design is a prototype with no independent review.
Reality
A dev.to survey walks seven AI supply chain entry points and the named incidents behind each. The two dataset-poisoning numbers in it are the ones that should change how a model review is scoped.
Reality
Seemant Sehgal, whose firm sells continuous penetration testing, says AI agents have cut the skill needed to run a full intrusion campaign. His evidence is two August 2025 incidents and one unmeasured claim about speed.
Reality
Checkmarx's lies-in-the-loop work shows the dialog a developer approves is rendered from the untrusted context the agent just read, metadata line included, which puts the last safeguard on the wrong side of the trust boundary.
Reality
Microsoft archived its prompt-injection framework on March 27, 2026. The tools that remain split into app-layer and model-layer work, and PyRIT was the only one configurable for both.
Reality