Back to skill

Security audit

a3-weather

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because scanners reported no issues in the completed scan and treated the flagged findings as likely purpose-related, but coverage was partial, so the evidence is incomplete.

The verdict is benign, but confidence is medium and Skillspector inspected only half of the reported components; one reference was missing and part of static analysis was degraded. Consider whether you trust the skill’s environment and network access, and review the incomplete coverage 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Code capability 'env' detected in scripts/weather.mjs but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Code capability 'network' detected in scripts/weather.mjs but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · scripts/weather.mjs (reported line 81)May include surrounding context.

js
async function getJson(kind, o, env, now) {
  const key = env.OPENWEATHER_API_KEY;
  if (!key) throw new WeatherError('OPENWEATHER_API_KEY is not set (add it to .env or the agent environment)', 2);
  const dir = env.A3_WEATHER_CACHE_DIR || path.join(os.tmpdir(), 'a3-weather-cache');
  const file = cacheFile(dir, kind, o);
  try {