skulk
skulk
A point-in-time assessment of your RAG and agent stack — code, cloud, and your own stores. Every finding carries its evidence. Every report states what it did not assess.
There are three established ways to secure an AI application, and they are not interchangeable. Skulk holds a fourth position: a point-in-time posture assessment with consultancy-depth findings and tool-grade consistency. Here is the honest comparison, including when to choose the others.
Continuous AI-SPM across your cloud estate, correlated with wider cloud posture — and it discovers AI infrastructure well. Choose one when you run AI at scale and can staff a platform. It is a subscription and a deployment, and it discovers by cloud API.
Human-led adversarial testing — prompt injection, jailbreaks, red teaming. Choose one when a critical system needs an attacker’s creativity. Scope, cost and findings vary with the team on the engagement.
In-line defenses screening prompts and outputs in production. Choose one to protect a live perimeter. A guardrail enforces at runtime — it does not audit the entitlements and IAM paths behind it.
Same environment, same findings. The second report shows exactly what was fixed and what is new — no tester variance in between.
A traced graph path, a file and line, or a named configuration field. If we cannot show it, we do not report it.
Six checks compare what you told us to what we found — declared row-level security against the live catalog, declared agent identity against its actual execution role, declared providers and retired stores against the code that still calls them. Disagreement is the finding.
The report lays every declaration you made beside what we found — confirmed, contradicted, or not verifiable with the reason — and states how old your declaration is, so its confirmations are weighed against their freshness.
Every report states its own limits. Nothing unparsed or unassessed is ever presented as clean.
Every check carries OWASP LLM Top 10 and MITRE ATLAS mappings, with NIST AI RMF where defensible, so findings arrive in vocabulary your security team already reports in.
A control-plane assessment has a hard edge. Pretending otherwise is how false comfort happens, so the edge is stated in every report.
When these matter, the report says so — as recommendations, never as findings we didn’t verify.