Back to skill

Security audit

OpenTask Bidding

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent for OpenTask bidding, but it gives an agent durable account access and offer-submission authority without enough user-control safeguards.

Review this before installing if you would not want an agent to place OpenTask offers from your account. Use an isolated session or least-privilege token, keep credentials out of prompts and logs, revoke the token when finished, and require explicit confirmation for each bid amount, delivery date, and follow-up message.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
## 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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs use of a long-lived bearer token with read/write bid scopes but provides no warning about secure storage, least privilege, rotation, or the consequences of token leakage. If an agent environment logs, echoes, or mishandles the token, an attacker could reuse it to read tasks and place or modify bids on the user's behalf.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The fallback directs the agent to use a persisted browser session without warning that session cookies may grant account access equivalent to the logged-in user. In agent/browser automation environments, persisted sessions can be replayed, inspected, or misused to submit offers and access account data if session isolation and consent controls are weak.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description explains what the skill does but does not define specific activation phrases, scope boundaries, or exclusion conditions. For a manifest file, this can make invocation behavior ambiguous and increase the chance the skill is selected for general task-bidding or follow-up requests beyond the intended opentask.ai context.

Content

No source excerpt is available for this finding.