The agent that grows with you
Python aiai-agentai-agentsanthropicchatgptclaudeclaude-codecodexhermeshermes-agentllmnous-researchopenai
feat(catalog): add airlock
Otsoa Dubief1ad1944a56af
diff --git a/plugin-catalog/airlock.yaml b/plugin-catalog/airlock.yamlnew file mode 100644index 00000000000..39a63c5467a--- /dev/null+++ b/plugin-catalog/airlock.yaml@@ -0,0 +1,53 @@+name: airlock+title: airlock+repo: https://github.com/otsoa-dubief/airlock+sha: c18f357a22153622ecdce71e07be64fe1bff3665+subdir: airlock+version: "0.2.0"+description: >-+ Guardrails that follow what a conversation has read. Once a session reads untrusted content (a web page, a+ browser snapshot, an MCP or third-party plugin's output, a customer's message), airlock seals it: messages to+ anyone but the owner, network writes, pushes and deploys, memory, skill and cron writes, browser input, URLs+ that could carry data out and code that reaches the network go through Hermes's own approval gate. Walls hold+ in every session: credential paths and secret files, the guard's own files and Hermes's config, shell startup+ files, other profiles, commands that switch approvals off. Shell commands are read the way the shell reads+ them, so a command that computes or hides what it runs (eval, base64 | sh, $G push, wildcards, write-then-run)+ is refused until written in clear. Subagents inherit the seal. It also catches an injection by its signature:+ recognized secrets never leave in a call; a private marker in the agent's context locks the session if it shows+ up in a tool call; a send to an address the untrusted content named is blocked; repeated refusals lock the+ session; lookalike Unicode in commands is refused. Plugin and MCP tools nobody admitted need+ approval. Observe mode, stop switch, `hermes airlock check|demo|log`. Tested on a corpus of 251 attacks+ and everyday commands, and end to end in the official image.+ Disclosure — hooks only (pre_tool_call, post_tool_call, pre_llm_call, subagent_start, on_session_reset,+ post_approval_response), no tools. No network, no LLM call, runs no command. Reads the profile's config.yaml+ (home channels, approvals mode) and its own policy file (<HERMES_HOME>/airlock.yaml); lists directories to+ expand wildcards in commands it checks. Writes under plugin-data/airlock: a journal of decisions, taints and+ approvals that includes tool arguments, truncated (journal.args: none leaves them out), the taint state and the+ stop switch. When nobody can approve (--yolo, approvals.mode: off, cron set to approve) it blocks instead of+ letting Hermes auto-approve (policy approvals_off: follow restores Hermes's behaviour). Install scan: caution,+ because the default policy and the shell reader name the patterns airlock guards against (startup files,+ crontab, credential commands, exfiltration shapes).+maintainer: otsoa-dubief+tier: community+category: tools+requires_hermes: ">=0.21.5"+docs_url: https://github.com/otsoa-dubief/airlock#readme+image: https://raw.githubusercontent.com/otsoa-dubief/airlock/c18f357a22153622ecdce71e07be64fe1bff3665/docs/images/social-preview.png+screenshots:+ - https://raw.githubusercontent.com/otsoa-dubief/airlock/c18f357a22153622ecdce71e07be64fe1bff3665/docs/images/live-session.gif+ - https://raw.githubusercontent.com/otsoa-dubief/airlock/c18f357a22153622ecdce71e07be64fe1bff3665/docs/images/how-it-works.png+ - https://raw.githubusercontent.com/otsoa-dubief/airlock/c18f357a22153622ecdce71e07be64fe1bff3665/docs/images/check.png+platforms: []+known_issues:+ - "Built for in-process plugins (Hermes's default): under plugins.isolation: host it cannot tell third-party plugin tools from Hermes's own."+capabilities:+ provides_tools: []+ provides_hooks:+ - pre_tool_call+ - post_tool_call+ - pre_llm_call+ - subagent_start+ - on_session_reset+ - post_approval_response+ provides_middleware: []+ requires_env: []