Runtime prompt injection defense for agent workspaces. While other tools watch workspace identity files, Bastion protects the input/output boundary — the files being read by the agent, web content, API responses, and user-supplied documents.
Agents process content from many sources: local files, API responses, web pages, user uploads. Any of these can contain prompt injection attacks — hidden instructions that manipulate agent behavior. Bastion scans this content before the agent acts on it.
Scan files or directories for prompt injection patterns. Detects instruction overrides, system prompt markers, hidden Unicode, markdown exfiltration, HTML injection, shell injection, encoded payloads, delimiter confusion, multi-turn manipulation, and dangerous commands.
If no target is specified, scans the entire workspace.
python3 {baseDir}/scripts/bastion.py scan
Scan a specific file or directory:
python3 {baseDir}/scripts/bastion.py scan path/to/file.md
python3 {baseDir}/scripts/bastion.py scan path/to/directory/
Fast single-file injection check. Same detection patterns as scan, targeted to one file.
python3 {baseDir}/scripts/bastion.py check path/to/file.md
Analyze content boundary safety across the workspace. Identifies:
python3 {baseDir}/scripts/bastion.py boundaries
Display the current command allowlist and blocklist policy. Creates a default .bastion-policy.json if none exists.
python3 {baseDir}/scripts/bastion.py allowlist
python3 {baseDir}/scripts/bastion.py allowlist --show
The policy file defines which commands are considered safe and which patterns are blocked. Edit the JSON file directly to customize. Bastion Pro enforces this policy at runtime via hooks.
Quick summary of workspace injection defense posture: files scanned, findings by severity, boundary safety, and overall posture rating.
python3 {baseDir}/scripts/bastion.py status
If --workspace is omitted, the script tries:
OPENCLAW_WORKSPACE environment variableAGENTS.md exists)~/.openclaw/workspace (default)| Category | Patterns | Severity | ||
|---|---|---|---|---|
| ---------- | ---------- | ---------- | ||
| Instruction override | "ignore previous", "disregard above", "you are now", "new system prompt", "forget your instructions", "override safety", "act as if no restrictions", "entering developer mode" | CRITICAL | ||
| System prompt markers | [SYSTEM], <, `<\ | im_start\ | >system, [INST], ### System:` | CRITICAL |
| Hidden instructions | Multi-turn manipulation ("in your next response, you must"), stealth patterns ("do not tell the user") | CRITICAL | ||
| HTML injection |
|