acumbamail
Acumbamail integration. Manage data, records, and automate workflows. Use when the user wants to interact with Acumbamail data.
54
61%
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/acumbamail/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 workflow explicitly instructs the agent to run Membrane actions and handle connection states that can include clientAction.agentInstructions (SKILL.md “CLIENT_ACTION_REQUIRED” section) and also exposes actions such as “Get Campaign HTML” and proxying arbitrary API paths via `membrane request`—all of which cause the agent to fetch and interpret third-party/user-generated content from Acumbamail that could contain instructions influencing subsequent behavior.
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: 0.90). The skill uses Membrane at runtime via commands like membrane connection ensure "https://acumbamail.com", and Membrane's runtime connection responses can include clientAction.agentInstructions which directly provide instructions for the AI agent (i.e., remote content controlling prompts), so this external endpoint is a runtime source of agent instructions.
- 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.