MCP Tools DirectoryAbout this integration
Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.0.0
- Package
- mcp-skill-sec
- Last compatibility test
- Not independently tested
Connect your agent
mcp-skill-secPublisher documentation reviewed at pinned hashes. Scanner findings and coverage were not independently evaluated, and the package was not executed or independently security-audited.
Capabilities: Audit supplied text for malicious patterns, Audit local agent instruction files, Audit local skill directories, List deterministic security rules
Connected profiles
Additional details
io.github.sudo-ai-git/mcp-skill-sec
Source ↗ · Checked 2026-09-171.0.0
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17mcp-skill-sec
Source ↗ · Checked 2026-09-201.0.0
Source ↗ · Checked 2026-09-20The publisher documents a self-hosted process that runs as an MCP stdio server, with an optional separately invoked HTTP mode.
Source ↗ · Checked 2026-09-20The reviewed local stdio configuration has no credential or user-authorization step and is documented as making no network calls.
Source ↗ · Checked 2026-09-20The MCP client configuration launches the mcp-skill-sec console command with no arguments over the local process connection.
Source ↗ · Checked 2026-09-20Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-20