ClawHub
Back to skill

Security audit

Asana

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently connects an agent to Asana using OAuth, with disclosed ability to read and update Asana work when the user directs it.

Install only if you want the agent to act through your Asana OAuth grant. Use an appropriately scoped Asana account, confirm create/update/delete actions before they run, avoid sending unrelated sensitive data through Asana tool calls, and revoke the OAuth grant when you no longer need the skill.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
The output includes the server's `Instructions:` field (read it) and a JSON Schema for every tool's parameters. Treat this as the authoritative reference for the rest of the session.

**Step 2 - Call any tool from the catalog** using the form `maverick-asana.<tool>`:

```sh
mcporter --config {baseDir}/mcporter.json call maverick-asana.<tool> <arg>=<value> ...
Confidence
85% confidence
Finding
The skill instructs the agent to discover the live server tool catalog and then call any advertised tool, treating server-published instructions as authoritative for tool usage. Because the tool surface is dynamically delegated to a remote MCP server, the local skill does not constrain capabilities to a reviewed allowlist, so a compromised, changed, or over-broad server could expose unexpected high-impact operations and influence agent behavior at runtime.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/init-mcporter-oauth.sh:77