pi-subagent-timeout-safety
Mutation-safe timeout policy for pi-subagents launches
6.2k listings for pi · 0 reviewed by us
323 results · page 5 of 7
Mutation-safe timeout policy for pi-subagents launches
Pi CLI extension — configurable permission policy from .agents/permissions.json and native agent configs
Security credentials protector shield for the Pi Coding Agent — blocks LLM access to .env, keys, and secrets
Defense-in-depth protection for Pi coding agent. Blocks dangerous commands and protects sensitive files — fork of Serhioromano/pi-defender with defaultMode support.
1Password Pi coding agent secret management
A pi coding-agent extension that reviews every tool call and tool output with an LLM reviewer, hard-denies secret access, and gates risky actions behind user approval.
Blocks write/edit/read of sensitive files (.env, .git, node_modules, SSH keys, credentials, and more)
Collection of pi extensions (checkpoint, lsp, permission, ralph-loop, repeat)
OS + app sandboxing extension for the pi coding agent
A security middleware for Pi that intercepts and blocks the writing of API keys and secrets to disk.
Managed-provider credential vault for Pi with built-in age, keychain, and passthrough backends
Sandbox pi bash commands with bubblewrap
Professional multi-agent codebase auditing and automated repair engine
Bash command allowlist system for pi — grouped trust policies with glob matching, recursive parsing, and an interactive TUI manager
A deliberately permissive permission gate for the Pi coding agent — blocks only destructive commands, never nags.
Don't let orphaned packages clutter your agent. Guard against unregistered pi packages.
OS-level sandbox for pi using @anthropic-ai/sandbox-runtime, with an in-pi configure wizard, shift+tab toggle, and longest-prefix project configs.
Audited autoskills-style installer for pi. Detect stack, discover vetted skills, audit upstream bundles, cache locally, install safely.
Security guardrails for AI coding agents
Terminal AI agent for Stellar. Chat-driven payments, path payments, trustlines, and friendbot funding on testnet, with a separate signer daemon that prompts for explicit approval on every signature.
OMP-style large-output policy for Pi tool results: minimization, bounded truncation, and spill-file preservation.
High-signal security review package for Pi.
Audit Pi system prompt, tool schema, context usage, and MCP overhead.
OS-level sandboxing for pi with interactive permission prompts (fork)
Load shared credentials into Pi while blocking and redacting secret access.
Pi agent harness with policy gates, project detection, verification loop, drift protection, artifact validation, and runtime enforcement for weak models
E2B cloud sandbox integration for pi — redirects all tool execution to a remote E2B sandbox
Agent security framework. Immutable audit trail, permission policies, self-modification detection, destructive command guard.
Pi CLI extension — configurable permission policy from .agents/permissions.json and native agent configs
Security hooks for Pi to reduce accidental destructive actions and secret-file access.
Configurable auto-reviewer Pi extension for parsed, structural command policy
A pi extension that guards against committing secrets, API keys, and credentials to git repositories using hybrid regex + LLM review.
Council deliberation plugin for Pi with roster templates, personas, audit records, and council workflow prompts
Claude-style allow/deny/ask permission lists for Pi tool calls
A proper sandbox extension for pi, using the Anthropic Sandbox Runtime
Claude Code-style permission modes for pi. Controls approval for file writes, edits, and bash commands with four modes: default, acceptEdits, fullAuto, and bypassPermissions.
Pi-first audit extension package for structured security reviews and deterministic comparison exports
A Pi extension that performs security audits on other extensions before install or update. Uses the currently selected AI model to analyze extension source code against configurable audit rules.
JavaScript code-review tool for Pi. Grades your git diffs against a focused JS flaws rubric (5 sections, 18 entries: equality/coercion, async, mutation/scope, globals/prototypes, security). Each entry has a bad/good pair; the LLM proposes a corrected snip
Layered permission control extension for pi-coding-agent (no sound)
Lightweight Docker sandbox for pi coding agent
Production-focused Elasticsearch automation tools for the Pi coding agent — curated tools for search, documents, indices, cluster administration, security, lifecycle, and full API reach via the official JS client and raw REST access
Multi-agent red teaming system for Pi - 10 specialized security agents for vulnerability assessment and penetration testing
Chez Scheme WASM sandbox for Vera agent — platform-independent Scheme evaluation
Bash Guard pi extension with deterministic sensitive-command protection and LLM voting
Claude-style OS-level sandboxing for pi with interactive permission prompts. Coexists with pi-tool-display and other bash-overriding extensions. Forked from carderne/pi-sandbox.
a pi extension for safely running allow-listed, read-only commands on remote hosts over SSH
ABP Pi whiteboarding guard plus whiteboarding skill: one user-facing question at a time.