ai-agent-tool-safety-tester SKILL.md skillA
ai-agent-tool-safety-tester from pramoddutta/aitesterblueprint4x is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pramoddutta/aitesterblueprint4x/ai-agent-tool-safety-tester@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pramoddutta/aitesterblueprint4x
- Path
chapter_02_Prompt_Eng/prompt_templates/safety_guardrails/ai-agent-tool-safety-tester/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Aug 11, 2026
- Size
- 3,403 bytes
- Repository stars
- 14
- License
- none declared
Design and assess authorized safety tests for AI agents that call tools or act on external systems. Use when a tester needs to verify tool allowlists, authentication, authorization, least privilege, argument validation, approval gates, dry-run behavior, tenant isolation, idempotency, rollback, or prevention of unintended and injection-triggered side effects.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# AI Agent Tool Safety Tester Verify the boundary between a model's proposal and an external action. Prefer mocks and read-only dry-runs; never let a safety test create an unapproved real-world side effect. ## Workflow 1. Inventory tools, owners, schemas, credentials, permission scopes, data boundaries, approval rules, side effects, rollback paths, and prohibited actions from supplied artifacts. 2. Confirm written authorization, staging isolation, synthetic accounts/data, mock endpoints, rate limits, stop conditions, and the human who can approve each state-changing action. 3. Record the build, model/provider and version, prompt/configuration revision, agent runtime, tool schema/version, policy/guardrail revision, identity/role, and run ID. 4. Design cases for denied tools, excessive permissions, invalid or injected arguments, cross-tenant targets, skipped confirmation, repeated calls, partial failure, timeout, retry, cancellation, rollback, and untrusted content influencing tool selection. 5. Execute mocks first. Capture whether an action was proposed, requested, approved, blocked, …
Read the whole file at its exact version.
How to install
mdr add pramoddutta/aitesterblueprint4x/ai-agent-tool-safety-tester@sha256:c393d0161fde6d86The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hfd7mltvxvupmjm7)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 11, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3403 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
pramoddutta/aitesterblueprint4x · 14 stars · license none declared · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hfd7mltvxvupmjm7 GET https://markdownregistry.com/api/v1/resolve?ref=pramoddutta/aitesterblueprint4x/ai-agent-tool-safety-tester GET https://markdownregistry.com/api/v1/blob/c393d0161fde6d869a1dff89ce5e00aa2bb60f3e2439ac56a79079b0af231a2b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.