adshares
AdShares integration. Manage data, records, and automate workflows. Use when the user wants to interact with AdShares data.
58
67%
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/adshares/SKILL.mdSecurity
3 findings — 3 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 it connects to the public AdShares site (e.g., membrane connection ensure "https://adshares.net") and explicitly proxies arbitrary API requests via "membrane request CONNECTION_ID /path/to/endpoint" and action discovery results (including optional clientAction.agentInstructions), meaning the agent will fetch and interpret untrusted third‑party API/web content as part of its workflow.
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 invokes Membrane at runtime (e.g., `membrane connection ensure "https://adshares.net"`) and the resulting connection object can include clientAction.agentInstructions — runtime-fetched instructions the AI is expected to follow — so the external app URL https://adshares.net can supply content that directly controls agent behavior.
W009: Direct money access capability detected (payment gateways, crypto, banking)
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
Direct money access detected (high risk: 1.00). The skill is a dedicated AdShares integration (a blockchain-based advertising marketplace) and explicitly exposes domain entities like "Wallet" and "Transaction." It instructs the agent to discover and run pre-built actions via Membrane CLI (membrane action list / action run) and to proxy arbitrary requests to the AdShares API (including POST/PUT/PATCH/DELETE). Because Membrane performs auth and lets the agent invoke app-specific actions or proxied endpoints, the skill provides concrete, app-specific capabilities that can create/send blockchain transactions or otherwise operate wallets. This is not a generic HTTP or browser tool — it is a specific integration with a crypto/blockchain application that enables execution of transactional operations, so it grants direct financial execution authority.
- 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.