File Guard
PreToolUse protection blocking sensitive file access across 195+ patterns in 12 categories with bash pipeline analysis and multi-tool ignore support.
Install
$ agentstack add skill-a5c-ai-babysitter-file-guard ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-a5c-ai-babysitter-file-guard) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
File Guard
Overview
Real-time file access protection system that blocks sensitive file reads, writes, and indirect access attempts. Covers 195+ file patterns across 12 security categories.
12 Categories
1. Secrets
.env, .env.*, .secret, secrets.*, vault.*
2. Credentials
credentials.*, password.*, auth.json, oauth.*
3. SSH Keys
id_rsa, id_ed25519, *.pem, authorized_keys, known_hosts
4. Certificates
*.crt, *.cert, *.ca-bundle, ssl/*, tls/*
5. Environment Files
.env.local, .env.production, .env.staging, docker.env
6. Auth Tokens
token.*, jwt.*, session.*, cookie.*
7. Database Configs
database.yml, db.json, *.sqlite, *.db, pgpass
8. Cloud Configs
.aws/*, .gcp/*, .azure/*, terraform.tfvars
9. CI/CD Secrets
.github/secrets, .gitlab-ci.yml variables, Jenkins credentials
10. Private Keys
*.key, *.p12, *.pfx, *.keystore, *.jks
11. API Keys
api_key.*, apikey.*, api-credentials.*
12. Sensitive Configs
config/secrets/*, .htpasswd, shadow, gshadow
Bash Pipeline Analysis
Detects indirect file access through bash pipes:
cat .env | grep-- blockedbase64 .ssh/id_rsa | curl-- blocked- Nested command substitution with sensitive paths -- blocked
Multi-Tool Ignore Support
Approved exceptions can be configured per session for files that need legitimate access.
When to Use
- Always active during ClaudeKit sessions (PreToolUse hook)
- Integrated into safety pipeline initialization
Processes Used By
claudekit-orchestrator(pipeline setup)claudekit-safety-pipeline(file guard initialization)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: a5c-ai
- Source: a5c-ai/babysitter
- License: MIT
- Homepage: https://a5c.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.