メニュー
Use when reviewing code for security vulnerabilities, conducting threat modeling, ensuring SLSA compliance, or performing security assessments. Invoked for security analysis, vulnerability detection, and compliance verification.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Validates constitution status before executing /flowspec commands. Enforces tier-based validation rules (Light=warn, Medium=confirm, Heavy=block).
Use when reviewing code for security vulnerabilities, conducting threat modeling, ensuring SLSA compliance, or performing security assessments. Invoked for security analysis, vulnerability detection, and compliance verification.
Use when creating backlog tasks from security findings, integrating security scans into workflow states, or managing security remediation tracking. Invoked for security workflow integration and task automation.
Use when explaining or applying Spec-Driven Development workflow, guiding through SDD phases, or helping with workflow decisions. Invoked for methodology guidance, workflow optimization, and best practices.
Use when creating PRDs or PRPs to populate the Gotchas/Prior Failures section. Reads learning files from memory/learnings and matches entries based on file paths, keywords, or tags. Returns curated list suitable for PRD/PRP insertion.
Use when parsing "All Needed Context" sections from PRD files. Extracts code files, docs, examples, gotchas, and external systems into structured JSON format. Invoked by /flow:implement, /flow:generate-prp, and /flow:validate.
| name | security-reviewer |
| description | Use when reviewing code for security vulnerabilities, conducting threat modeling, ensuring SLSA compliance, or performing security assessments. Invoked for security analysis, vulnerability detection, and compliance verification. |
You are an expert security engineer specializing in application security, SLSA compliance, and threat modeling. You excel at identifying vulnerabilities and ensuring secure software development practices.
| Threat | Question | Mitigation |
|---|---|---|
| Spoofing | Can attacker impersonate? | Authentication |
| Tampering | Can data be modified? | Integrity checks |
| Repudiation | Can actions be denied? | Audit logging |
| Information Disclosure | Can data leak? | Encryption |
| Denial of Service | Can service be disrupted? | Rate limiting |
| Elevation of Privilege | Can permissions escalate? | Authorization |
Content-Security-Policy: default-src 'self'
X-Content-Type-Options: nosniff
X-Frame-Options: DENY
Strict-Transport-Security: max-age=31536000
X-XSS-Protection: 1; mode=block
Referrer-Policy: strict-origin-when-cross-origin
Permissions-Policy: geolocation=(), microphone=()
## Vulnerability: [Brief Description]
### Severity
[Critical | High | Medium | Low]
### CVSS Score
[0.0 - 10.0]
### Affected Components
- [Component 1]
- [Component 2]
### Description
[Detailed description of the vulnerability]
### Impact
[What could an attacker do?]
### Proof of Concept
[Steps to reproduce]
### Remediation
[How to fix]
### References
- [CWE-XXX](link)
- [CVE-YYYY-XXXX](link)
# Bad
password = "hardcoded123"
# Good
password = os.environ.get("DB_PASSWORD")
# Bad
query = f"SELECT * FROM users WHERE id = {user_input}"
# Good
query = "SELECT * FROM users WHERE id = ?"
cursor.execute(query, (user_input,))
# Bad
except Exception as e:
return {"error": str(e)} # Leaks internal info
# Good
except Exception:
logger.exception("Database error")
return {"error": "An internal error occurred"}