Paveo: shared pre-tool rules for Claude Code, Codex, Cursor
Local gate: one policy set so Claude Code/Codex/Cursor check with Paveo before shell or file write; dangerous actions refused, every decision logged—no network required.
Topic
agent-security use cases: 6 examples
Source-linked workflows that name agent-security. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
heldkeys: list credentials your coding agent can reach
Read-only CLI that inventories env/CLI/.env/MCP/SSH/cloud logins an agent inherits on laptop, sandbox, or CI—and flags risky agent steps in GitHub Actions—without printing secret values.
AISLE MCP + package firewall: prove, fix, and block in the IDE
AISLE October rollout (Oct 14): MCP server puts exploit-proven findings into Claude Code/Cursor so agents fix in-editor; plus an AI package firewall that intercepts npm/PyPI/Cargo installs from humans and coding agents, with cooldown and monitoring mode before enforcement.
Chainguard MCP GA: four OAuth servers for agent dependency checks
Enterprise GA for cg-oci, cg-apk, cg-versions, and cg-api so Claude Code/Cursor agents verify image tags, Wolfi package equivalents, EOL status, and org policy/attestations via browser OAuth or chainctl—server-side caps instead of prompt guardrails.
Anaconda MCP GA: remote read-only package facts for agents
Remote MCP at anaconda.com/api/mcp returns package facts, curated CVEs, org channel policy, and forum hits so Claude Code/Cursor/Codex/Kilo check real conda names and vulns before proposing installs—server cannot mutate your machine; agent still runs conda under your permissions.
OpenAPPA: deterministic flow-label guardrails that don't break agents
Open-source MIT guardrail tracks audience×trust labels across tool calls (algebra, not LLM-as-judge), returns remedy plans (sanitize/authority/subagent) so agents keep ~90% task completion with 0% exfil on their benches—plugs via pre/post tool hooks; docs also as MCP.