AddressFinder Australia integration. Manage data, records, and automate workflows. Use when the user wants to interact with AddressFinder Australia data.
39
37%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/addressfinder-australia/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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.
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.
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.
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.
f484c82
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.