agentguard
by manas-io-ai
DevOps & CloudBrief
**Category:** Security & Monitoring.
Description
What This Skill Does
Monitors agent file access, outbound API calls, and external communications to detect suspicious behavior. Generates security reports and sends alerts with configurable severity thresholds. All processing runs locally with no external data transmission.
Runs entirely locally with no external data transmission, so sensitive operational data stays on the machine while still providing full audit trails and ML-lite anomaly detection.
When to Use It
- Detecting when an agent reads credential files like .env or API key files
- Auditing outbound HTTP calls made by a running agent during a session
- Generating a daily security summary of agent activity and anomalies
- Investigating file access patterns over a specific time window after a suspected issue
- Flagging bulk file reads that match data exfiltration patterns
Example Workflow
User asks: 'What has my agent been doing with files in the last 2 hours?'
- 1
Run
agentguard startto confirm monitoring is active - 2
Run
agentguard investigate --timerange 'last 2 hours' --type file_access - 3
Review returned events grouped by severity level
- 4
Run
agentguard alerts --last 24h --severity highto check for flagged incidents - 5
Run
agentguard report --nowfor a full activity summary
A breakdown of file access events with severity labels, any triggered alerts, and a list of accessed resource paths from the past two hours
Installation
clawhub install manas-io-ai/agentguardRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.