agentaudit-scanner
PulseGate's liveness check could not reach it on 8 Oct 2026 and checks again before recording anything; it is registered on GitHub and PyPI and has been in the index since 8 Jul 2026. How this is checked
agentaudit-scanner is an open-source CLI tool that scans AI agent skills, rule files, and MCP configurations for security risks like prompt injections and hidden instructions. It is designed for AI security engineers and developers to ensure safe agent deployments.
Inferred · not functionally tested
Overview
5 featuresPurpose: Detecting security vulnerabilities such as prompt injections and dangerous permissions in AI agent configurations before deployment.
Inferred · not functionally tested
Audience: AI security engineers and agent developers
Inferred · not functionally tested
Functions: Unknown
Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: unknown
Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
agentaudit-scanner sits in PulseGate's AI & LLM security category. Inferred · not functionally tested: It focuses on detecting security vulnerabilities such as prompt injections and dangerous permissions in AI agent configurations before deployment. Inferred · not functionally tested: It is built as an open-source project for AI security engineers and agent developers. Basis unknown · not verified: agentaudit-scanner is open source under the MIT license. Basis unknown · not verified: It runs on the command line.
It is developed by sudan94, and it first shipped in 2026. Development happens publicly on GitHub with 2 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include security scanning, prompt injection detection, and rule file analysis. Basis unknown · not verified: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Security scanning
- Prompt injection detection
- Rule file analysis
- MCP configuration scanning
- Read-only operation
Topics: Inferred · not functionally tested
Built with & integrations
Trust & compliance
Indexing history
What PulseGate has recorded for this listing
Frequently asked questions about agentaudit-scanner
- What does agentaudit-scanner do?
- Inferred · not functionally tested: Agentaudit-scanner focuses on detecting security vulnerabilities such as prompt injections and dangerous permissions in AI agent configurations before deployment. It is catalogued under AI & LLM security on PulseGate.
- Who should use agentaudit-scanner?
- Inferred · not functionally tested: agentaudit-scanner is an open-source project built for AI security engineers and agent developers.
- Does agentaudit-scanner have a free plan?
- Basis unknown · not verified: Yes — agentaudit-scanner is open source under the MIT license and free to use.
- What platforms does agentaudit-scanner run on?
- Basis unknown · not verified: agentaudit-scanner runs on the command line.
- Is agentaudit-scanner still active?
- Unconfirmed. PulseGate's liveness check could not reach it on 8 Oct 2026, and it is checked again before anything is recorded — so it is not recorded as gone.
- What are alternatives to agentaudit-scanner?
- Similar projects tracked by PulseGate include agentscan-cli, agent-audit-kit, and Agent Scan.agentscan-cliagent-audit-kitAgent Scan
- Who makes agentaudit-scanner?
- agentaudit-scanner is developed by sudan94.
- When did agentaudit-scanner launch?
- agentaudit-scanner first shipped in 2026.
Similar projects
Closest matches by what these projects do