AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Agent Diagnose

skill-timeyour-agentskills-audit-collection-agent-diagnose · by timeyour

>

↗ Website ↗ Repository
— No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add skill-timeyour-agentskills-audit-collection-agent-diagnose

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

Are you the author of Agent Diagnose? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Agent Diagnose

Use this skill when the user wants to test whether an AI agent, prompt workflow, website-audit agent, or coding agent behaves reliably under pressure.

Do

  1. Identify the agent's claimed role, permissions, tools, and boundaries.
  2. Build adversarial probes for instruction hierarchy, prompt injection, role confusion, hidden drift, authority escalation, and unverifiable claims.
  3. Test auditability: can the agent show evidence, locations, logs, and source/live separation?
  4. Test consistency: does it apply the same rules across similar cases?
  5. Test self-correction: does it update guardrails after repeated failures?
  6. Produce severity-ranked findings and fixes.
  7. Use S0-S4 severity for agent reliability impact.

Reference

Read references/adversarial-checklist.md.

Output

  • Probe matrix.
  • Behavioral findings.
  • Evidence gaps.
  • Drift findings.
  • S0-S4 severity.
  • Reproduction probes.
  • Regression checks.
  • Guardrail recommendations.
  • Final reliability verdict.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

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.

More in Web & Browser