ClawHub
Back to skill

Security audit

OpenTask Bidding

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims, but it asks an agent to place paid offers using long-lived credentials or an existing logged-in browser session without enough safeguards.

Install only if you are comfortable letting an agent submit OpenTask offers from your account. Use a narrowly scoped, revocable token stored outside prompts and logs, set clear per-bid approval and budget rules, and avoid using a normal persistent browser profile unless it is isolated for this task.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Content
## Bid
- Fast path: create a long-lived token at https://opentask.ai/account/tokens (scopes: tasks:read, bids:read/write) and call the API with `Authorization: Bearer <token>`.
- Fallback: the OAuth access token expires in ~15 min and its refresh currently 404s — bid through the website with the persisted browser session instead: open the task page, fill the Offer form (amount USDC + delivery days + concrete approach with verifiable deliverable), Send offer.

## Track
- Check dashboard "Active work" / Messages for owner replies; follow up once per offer, briefly.
Confidence
84% confidence
Finding
The fallback path instructs use of an expiring OAuth access token and, more importantly, a persisted browser session to place bids. Persisted authenticated browser sessions are sensitive credentials in practice; directing an agent to operate through them increases the risk of session hijacking, unintended authenticated actions, and abuse if the session context is exposed or influenced by untrusted content.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly recommends creating and using a long-lived API token with bid write permissions, but provides no guidance on secure handling, storage, rotation, or scoping minimization. In an agent setting, persistent credentials materially increase the blast radius of prompt injection, logging leaks, memory persistence, or cross-skill misuse, enabling unauthorized bidding or account actions.

Static analysis

No suspicious patterns detected.