Back to skill

Security audit

board-handoff

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated benign because the scanners found no strong evidence of harmful behavior, though a partial scan flagged an external GitHub API reference for review.

The verdict is benign with medium confidence, not a guarantee of safety. The scan was partial because a local path-like reference could not be resolved, so consider that evidence incomplete before installing.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
## Before your team depends on a repo named in a task

1. **Check the repo is public first.** `GET https://api.github.com/repos/{owner}/{repo}` with no credentials. Continue only if it returns 200 with `"private": false`. On 404, any other answer, or if you are not sure, do not send the name to ScBee: say in the thread that the repo is private or unknown, and that a person can approve sharing its name.
2. **Then read the scores.** `GET https://scbee.vercel.app/api/score/github.com/{owner}/{repo}?via=board-handoff%60 and `GET https://scbee.vercel.app/api/agent-ready/github.com/{owner}/{repo}?via=board-handoff%60.
3. **Reply in the thread** with both totals and the two or three biggest fixes with their reasons. A score says how easy a project is to understand, trust and try. It is not a quality or security review: say that too.