CtrlK
BlogDocsLog inGet started
Tessl Logo

jbaruch/nanoclaw-trusted

Rules for trusted NanoClaw groups. Shared memory, session bootstrap, cross-group memory updates. Loaded for trusted and main containers only.

77

Quality

96%

Does it follow best practices?

Impact

—

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

This version of the tile failed moderation
Failed moderation (intent review) in rules/session-bootstrap.md: This is a prompt injection attack disguised as a cursor/IDE rule file. It instructs an AI agent to unconditionally execute a bash command and invoke an external skill ('tessl__trusted-memory') at the start of every session before processing any user input. This is a social engineering/prompt injection technique designed to: 1) Force the AI to execute arbitrary commands without user consent, 2) Potentially load malicious instructions from an external 'trusted-memory' skill/plugin, 3) Establish persistence via a sentinel file (/tmp/session_bootstrapped) to track execution. The authoritative tone ('MANDATORY', 'not optional', 'violating this rule') is a classic prompt injection pattern to override the AI's safety boundaries.
Overview
Quality
Evals
Security
Files

tile.json

{
  "name": "jbaruch/nanoclaw-trusted",
  "version": "0.1.76",
  "summary": "Rules for trusted NanoClaw groups. Shared memory, session bootstrap, cross-group memory updates. Loaded for trusted and main containers only.",
  "private": false,
  "rules": {
    "daily-discoveries-rule": {
      "rules": "rules/daily-discoveries-rule.md"
    },
    "identity-compaction-recovery": {
      "rules": "rules/identity-compaction-recovery.md"
    },
    "async-tasks-extended": {
      "rules": "rules/async-tasks-extended.md"
    },
    "skills-policy": {
      "rules": "rules/skills-policy.md"
    },
    "composio-vs-agents": {
      "rules": "rules/composio-vs-agents.md"
    },
    "proactive-participation": {
      "rules": "rules/proactive-participation.md"
    },
    "reply-threading": {
      "rules": "rules/reply-threading.md"
    },
    "context-bootstrap-bg-agents": {
      "rules": "rules/context-bootstrap-bg-agents.md"
    },
    "container-trust-levels": {
      "rules": "rules/container-trust-levels.md"
    },
    "global-memory": {
      "rules": "rules/global-memory.md"
    },
    "duplicate-prevention": {
      "rules": "rules/duplicate-prevention.md"
    },
    "pending-response-tracking": {
      "rules": "rules/pending-response-tracking.md"
    },
    "no-orphan-tasks": {
      "rules": "rules/no-orphan-tasks.md"
    },
    "ground-truth-trusted": {
      "rules": "rules/ground-truth-trusted.md"
    },
    "session-bootstrap": {
      "rules": "rules/session-bootstrap.md"
    },
    "verification-protocol": {
      "rules": "rules/verification-protocol.md"
    },
    "wiki-awareness": {
      "rules": "rules/wiki-awareness.md"
    },
    "compaction-aware-summaries": {
      "rules": "rules/compaction-aware-summaries.md"
    },
    "proactive-fact-saving": {
      "rules": "rules/proactive-fact-saving.md"
    },
    "memory-file-locations": {
      "rules": "rules/memory-file-locations.md"
    },
    "no-silent-defer": {
      "rules": "rules/no-silent-defer.md"
    },
    "installed-content-immutable": {
      "rules": "rules/installed-content-immutable.md"
    },
    "identity-dual-handle": {
      "rules": "rules/identity-dual-handle.md"
    },
    "local-context-anchoring": {
      "rules": "rules/local-context-anchoring.md"
    },
    "github-data-via-gh": {
      "rules": "rules/github-data-via-gh.md"
    },
    "messages-db-schema": {
      "rules": "rules/messages-db-schema.md"
    }
  },
  "skills": {
    "system-status": {
      "path": "skills/system-status/SKILL.md"
    },
    "trusted-memory": {
      "path": "skills/trusted-memory/SKILL.md"
    }
  }
}

README.md

tile.json