Atlassian Forge Skills supports Atlassian Forge, a platform for building and deploying apps that extend products such as Jira and Confluence. Its skills and MCP-backed tools help coding agents create Forge apps, review them before deployment, optimize usage, troubleshoot failures, and work with Forge APIs and the Atlassian Design System.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/atlassian/forge-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/atlassian/forge-skills/_index-tenant-isolation)<a href="https://agentmods.dev/rules/atlassian/forge-skills/_index-tenant-isolation"><img src="https://agentmods.dev/badge/rules/atlassian/forge-skills/_index-tenant-isolation.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00428 |
| Opus 5 | $0.00000 | $0.00214 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
_index-tenant-isolation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
- Scope: Multi-tenant data isolation, Lambda warm start risks, global state, and cross-tenant data leakage.
- Priority: Critical for Marketplace apps serving multiple customers on shared infrastructure.
Key Forge Tenant Isolation Risks
- Lambda warm start behavior: AWS Lambda reuses runtime instances; global variables persist across invocations from different tenants.
- Module-level state pollution: Caches, feature flags, and configuration stored at module scope can leak between tenants.
- Storage key collisions: Improperly scoped storage keys can allow cross-tenant data access.
- Cross-tenant API calls:
requestGraphand__requestAtlassianhistorically enabled cross-tenant access.
Subrules
- Global State and Warm Start →
@forge-tenant-isolation/global-state-warmstart.mdc
Detection Heuristics
- Identify module-level variables (
const cache = {},let state = ...) outside handler functions. - Search for caches that don't include tenant/installation context in keys.
- Review storage operations for tenant-scoped key prefixes.
- Check for user script execution that can access/modify global scope.
Forge-Specific Caveats
- RuntimeV2 uses AWS Lambda isolation instead of V1's custom sandbox, shifting tenant isolation responsibility to app developers.
- User-supplied code execution (like JMCF scripted fields) in shared global scope is high risk.
CWE References
- CWE-668: Exposure of Resource to Wrong Sphere
- CWE-200: Information Exposure
- CWE-212: Improper Removal of Sensitive Information Before Storage or Transfer
- CWE-1189: Improper Isolation of Shared Resources
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 44 lines · 0 tokens per session scan A 2c94aac68811
_index-tenant-isolation is a cursor rule published in the GitHub repository atlassian/forge-skills (21 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 428 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.