Security Audit
Run a security-focused code audit with a generic checklist first, then layer on repo-specific risks.
Install
$ agentstack add skill-stella-skillguard-security-audit ✓ 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 No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ 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-stella-skillguard-security-audit) 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
Security Audit
Run a security-focused code audit with a generic checklist first, then layer on repo-specific risks.
Instructions
- Start with repo context:
- what kind of system is this?
- what data does it handle?
- what are the trust boundaries?
- what would be high-impact failures here?
- Check for hardcoded secrets:
- API keys
- tokens
- passwords
- private connection strings
- Review authentication and authorization:
- are protected routes actually protected?
- are object/resource ownership checks enforced server-side?
- are role checks done at the boundary, not just in the UI?
- Review input handling:
- validation present for user-controlled inputs
- no obvious SQL injection, command injection, XSS, or path traversal
- file paths, URLs, and object keys are sanitized appropriately
- Review file and storage access when relevant:
- upload validation
- download/presign access checks
- safe retention/deletion behavior
- Review network and session behavior:
- sane session expiration and invalidation
- rate limits where brute force is plausible
- external requests have timeouts and failure handling
- CORS is not broader than necessary
- Review dependency risk:
``bash bun audit ``
Use the repo's equivalent audit command if it does not use Bun. Also check GitHub security or Dependabot alerts when available.
- Review AI-specific risks when applicable:
- prompt injection exposure
- unsafe interpolation of user content into system instructions
- cross-tenant or cross-document leakage through retrieval/context assembly
- Layer in domain-specific risks:
- finance, healthcare, legal, infra, auth, multi-tenant SaaS, and internal tools
all have different sharp edges
- explicitly call out the domain assumptions you used
- Report findings by severity:
- Critical
- High
- Medium
- Low
For each finding include:
- file and line
- issue
- likely impact
- recommended fix
- If there are no findings, say so explicitly and mention what was checked
plus any residual gaps in verification.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: stella
- Source: stella/skillguard
- License: Apache-2.0
- Homepage: https://stll.app
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.