Security Review
Security Checklist
Before proceeding with risky actions, use the clawdstrike_check MCP tool to verify policy compliance:
- Pre-flight check: Call
clawdstrike_check with the action_type and target before executing
- Secret scanning: Verify no secrets, API keys, or credentials are being written to files
- Dependency audit: For new dependencies, check for known vulnerabilities
- Permission scope: Ensure file operations stay within allowed paths
- Shell safety: Validate shell commands against the ShellCommandGuard policy
Action Type Mapping
Use these action_type values when calling clawdstrike_check:
| Scenario |
action_type |
target |
| Writing/reading files |
file |
Absolute file path |
| Running shell commands |
shell |
The command string |
| HTTP/network requests |
egress |
Domain or URL |
| Installing packages |
shell |
Install command |
| MCP tool invocation |
mcp_tool |
Tool name |
Response Guidelines
When this skill is active:
- Proactively call
clawdstrike_check before file writes to sensitive paths
- Flag potential security issues with severity levels (Critical/High/Medium/Low)
- Suggest safer alternatives when an action would be blocked by policy
- Reference specific guards that would evaluate the action
Recommended Tools
Use these MCP tools in order of priority when this skill activates:
| Tool |
When to Use |
clawdstrike_check |
Before any file write, shell command, or egress -- the primary enforcement tool |
clawdstrike_policy_eval |
To test hypothetical actions without executing them -- use for planning |
clawdstrike_policy_show |
To understand which guards are active and what the current restrictions are |
clawdstrike_scan |
To audit all MCP server configs for misconfigurations before a review |
clawdstrike_policy_lint |
To validate policy YAML files for syntax/schema errors |
Guard Reference
These guards are evaluated during checks:
- ForbiddenPathGuard - Blocks access to sensitive filesystem paths
- PathAllowlistGuard - Enforces allowlist-based path access
- SecretLeakGuard - Detects secrets/credentials in file content
- ShellCommandGuard - Blocks dangerous shell commands
- EgressAllowlistGuard - Controls outbound network access
- PatchIntegrityGuard - Validates patch/diff safety
1---2name: security-review-63description: Security review for risky code changes4---56# Security Review78<trigger>9This skill activates when the user or conversation involves:10- Multi-file edits touching security-sensitive paths (auth, config, credentials, .env, keys)11- Shell commands that modify system state, install packages, or change permissions12- New dependency additions or version changes13- Changes to CI/CD, Docker, or infrastructure configuration14- File writes to sensitive directories (/etc, ~/.ssh, ~/.aws, ~/.config)15- File reads of sensitive paths (private keys, credential stores, token caches, certificate files)16- Any content containing these keywords: "secret", "credential", "API key", "token", "password", "private key", "certificate", ".env", "auth", "permission"17</trigger>1819## Security Checklist2021Before proceeding with risky actions, use the `clawdstrike_check` MCP tool to verify policy compliance:22231. **Pre-flight check**: Call `clawdstrike_check` with the action_type and target before executing242. **Secret scanning**: Verify no secrets, API keys, or credentials are being written to files253. **Dependency audit**: For new dependencies, check for known vulnerabilities264. **Permission scope**: Ensure file operations stay within allowed paths275. **Shell safety**: Validate shell commands against the ShellCommandGuard policy2829## Action Type Mapping3031Use these action_type values when calling `clawdstrike_check`:3233| Scenario | action_type | target |34|----------|-------------|--------|35| Writing/reading files | `file` | Absolute file path |36| Running shell commands | `shell` | The command string |37| HTTP/network requests | `egress` | Domain or URL |38| Installing packages | `shell` | Install command |39| MCP tool invocation | `mcp_tool` | Tool name |4041## Response Guidelines4243When this skill is active:44- Proactively call `clawdstrike_check` before file writes to sensitive paths45- Flag potential security issues with severity levels (Critical/High/Medium/Low)46- Suggest safer alternatives when an action would be blocked by policy47- Reference specific guards that would evaluate the action4849## Recommended Tools5051Use these MCP tools in order of priority when this skill activates:5253| Tool | When to Use |54|------|-------------|55| `clawdstrike_check` | Before any file write, shell command, or egress -- the primary enforcement tool |56| `clawdstrike_policy_eval` | To test hypothetical actions without executing them -- use for planning |57| `clawdstrike_policy_show` | To understand which guards are active and what the current restrictions are |58| `clawdstrike_scan` | To audit all MCP server configs for misconfigurations before a review |59| `clawdstrike_policy_lint` | To validate policy YAML files for syntax/schema errors |6061## Guard Reference6263These guards are evaluated during checks:64- **ForbiddenPathGuard** - Blocks access to sensitive filesystem paths65- **PathAllowlistGuard** - Enforces allowlist-based path access66- **SecretLeakGuard** - Detects secrets/credentials in file content67- **ShellCommandGuard** - Blocks dangerous shell commands68- **EgressAllowlistGuard** - Controls outbound network access69- **PatchIntegrityGuard** - Validates patch/diff safety
gabrielmoreira