AI, agents and MCP
Prompt injection, RAG poisoning, MCP servers, agent permissions and model supply chain.
Assessing LLM apps and agents: tool output trust, MCP server code audits, sandbox and secret exposure, model artifacts, vector database security and AI red team test plans.
Results
15 entries
testing-prompt-injection-in-rag-pipelines
Highmukul975/testing-prompt-injection-in-rag-pipelinesAI, agents and MCP4 installs, 4 installs in the last 7 days, 36,301 stars on GitHubimplementing-llm-guardrails-for-security
Highmukul975/implementing-llm-guardrails-for-securityAI, agents and MCP4 installs, 4 installs in the last 7 days, 36,301 stars on GitHubdefending-llms-with-guardrails
Highmukul975/defending-llms-with-guardrailsAI, agents and MCP4 installs, 4 installs in the last 7 days, 36,301 stars on GitHubtesting-for-system-prompt-leakage
Highmukul975/testing-for-system-prompt-leakageAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubdetecting-indirect-prompt-injection
Highmukul975/detecting-indirect-prompt-injectionAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubdetecting-ai-model-prompt-injection-attacks
Highmukul975/detecting-ai-model-prompt-injection-attacksAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubauditing-mcp-servers-for-tool-poisoning
Highmukul975/auditing-mcp-servers-for-tool-poisoningAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubassessing-vector-and-embedding-weaknesses
Highmukul975/assessing-vector-and-embedding-weaknessesAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubsecuring-agentic-ai-tool-invocation
Mediummukul975/securing-agentic-ai-tool-invocationAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubred-teaming-llms-with-garak
Mediummukul975/red-teaming-llms-with-garakAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubperforming-ai-driven-osint-correlation
Mediummukul975/performing-ai-driven-osint-correlationAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHuborchestrating-llm-attacks-with-pyrit
Mediummukul975/orchestrating-llm-attacks-with-pyritAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubdetecting-model-extraction-attacks
Mediummukul975/detecting-model-extraction-attacksAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubdetecting-business-email-compromise-with-ai
Mediummukul975/detecting-business-email-compromise-with-aiAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHubcontinuous-llm-red-teaming-with-promptfoo
Mediummukul975/continuous-llm-red-teaming-with-promptfooAI, agents and MCP3 installs, 3 installs in the last 7 days, 36,301 stars on GitHub
Filters
Ask anything your scope allows.
Create an account, add credits and ask the first question in the chat or the terminal.
- 1/3
Create the account
Individual or company. You can switch to a company later without losing balance or keys.
IndividualCompany - 2/3
Add credits
By card. Pay per token, no subscription.
$5.00minimum deposit - 3/3
Ask
In the chat, or install the CLI and run notholy login in your terminal.
$ notholy login