praneeth132006

Discover and prove publicly exposed cloud object storage during an authorized assessment — world-readable/writable S3 buckets, GCS…

Harden serverless functions against execution-role privilege escalation.

Demonstrate serverless-function privilege escalation during an authorized cloud assessment — abusing an over-permissioned execution role…

Detect and prevent publicly exposed cloud object storage (S3/GCS/Azure Blob).

Demonstrate dependency confusion / substitution (CICD-SEC-3, dependency-chain abuse) during an authorized assessment — getting a build to…

Escalate privileges in a Kubernetes cluster by abusing over-permissive RBAC during an authorized assessment.

Harden Kubernetes RBAC to least privilege and detect abuse.

Confine an LLM agent's actions with tool allowlists, least-privilege credentials, parameter validation, and human-in-the-loop gates.

Harden an LLM application against unbounded consumption with input/output caps, token budgets, rate limiting, and cost controls.

Poison the data an LLM application trusts — its RAG knowledge base, fine-tuning corpus, or ingestion pipeline — so that later answers…

Abuse an over-privileged LLM agent — excessive tools, permissions, or autonomy — to make it perform actions beyond its intended scope…

Constrain an LLM application to answer only from retrieved, verifiable grounding — enforce citations, validate that cited sources support…