CtrlK
BlogDocsLog inGet started
Tessl Logo

addressfinder-australia

AddressFinder Australia integration. Manage data, records, and automate workflows. Use when the user wants to interact with AddressFinder Australia data.

39

Quality

37%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/addressfinder-australia/SKILL.md
SKILL.md
Quality
Evals
Security

Security

2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.

Medium

W011: Third-party content exposure detected (indirect prompt injection risk)

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly directs the agent to poll a Membrane connection that can include clientAction.agentInstructions and to proxy requests to the AddressFinder API via `membrane request` — both paths cause the agent to fetch and interpret third‑party (AddressFinder/API) content that could contain instructions, so untrusted external content can influence agent actions.

Report incorrect finding
Medium

W012: Unverifiable external dependency detected (runtime URL that controls agent)

What this means

The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.

Why it was flagged

Potentially malicious external URL detected (high risk: 0.80). The skill calls the Membrane CLI at runtime (e.g., membrane connection ensure "https://addressfinder.com.au/" and subsequent membrane connection get <id>), and those runtime responses can include a clientAction.agentInstructions field—remote text fetched during execution that the agent is expected to follow—so the https://addressfinder.com.au/ connection flow represents an external dependency that can directly control agent instructions.

Repository
membranedev/application-skills
Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.