Back to skill

Security audit

deadline-radar

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill benign because the reported network access and deadline-check behavior appear related to its purpose, though some concerns and incomplete inspection keep confidence medium.

Consider that the scan was partial: it inspected 4 of 5 components, and static analysis of one file was incomplete. Before installing, check that you are comfortable with its GitHub API access, unclear tool scope, and possible mismatch between commit age and push activity.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/radar.mjs (reported line 61)May include surrounding context.

js
const repo = spec.slice("github:".length);
  if (!/^[\w.-]+\/[\w.-]+$/.test(repo)) return { kind: "github", error: "invalid github:owner/repo" };
  try {
    const res = await fetch(`https://api.github.com/repos/${repo}/commits?per_page=1%60, {
      headers: { Accept: "application/vnd.github+json", "User-Agent": "deadline-radar" },
      signal: AbortSignal.timeout(10000),
    });

GitHub activity checks measure commit age, not time since the last push as promised by the manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

L061-L068 fetch the latest commit and label its committer timestamp as lastPushAt, although a commit timestamp does not record when it was pushed to GitHub. Consequently, the risk assessment can report stale push activity immediately after older commits are pushed, undermining the manifest's promised push-based deadline check.

Content

No source excerpt is available for this finding.

The activation phrase "am I on track" is overly broad and lacks a deadline-specific constraint.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

"Am I on track" is common in conversations about fitness, finances, learning, and other topics unrelated to repository deadlines. Although the description explains the skill's purpose, it does not restrict this trigger to requests about DEADLINES.md or repository-linked deadlines.

Content

No source excerpt is available for this finding.