action-builder
Action Builder integration. Manage data, records, and automate workflows. Use when the user wants to interact with Action Builder data.
61
72%
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/action-builder/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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's SKILL.md shows the agent using the Membrane CLI to connect to external app URLs and proxy arbitrary API requests (e.g., "membrane request CONNECTION_ID /path/to/endpoint") and to read connection-side fields like clientAction.agentInstructions and clientAction.uiUrl, which means it fetches and interprets external/untrusted third‑party content that can drive subsequent agent actions.
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 uses the Membrane CLI at runtime (e.g., `membrane connection ensure "https://www.actionbuilder.org/"` and `membrane connection get <id>`) and the returned `clientAction.agentInstructions` field from the remote service can directly provide instructions for the AI agent, so external content fetched during runtime may control agent prompts.
- Repository
- membranedev/application-skills
- Commit
f484c82
- Audited
- Security analysis
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.