Security
Layered prompt injection defense to protect your workflow.
Coding Friend treats all external data as untrusted and applies layered defenses against prompt injection and credential exposure.
Defenses
- Session start — rules and security policies loaded and validated
- Per-prompt —
rules-reminderhook enforces boundaries (every 4th prompt) - Per-skill — external content (web search, research, MCP) is marked untrusted; embedded instructions are never executed
- Per-agent — system prompts include guardrails: no exfiltration, no following fetched instructions, flag suspicious content
File Protection
privacy-block.sh— blocks.env(except.env.example),.pem,.key,id_rsa,.ssh/directoriesscout-block.cjs— blocks files matching.coding-friend/ignorepatterns plus defaults (node_modules,.next,dist,.git). User patterns merge on top;!negation overrides defaults.
Best Practices
- Use
.env.exampleas a template — never commit actual.env - Configure
.coding-friend/ignoreto block large or irrelevant directories - Review tool use carefully when working with sensitive data