Back to skill

Security audit

Open-Meteo Day Brief

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this weather-briefing skill as benign because the reported network access and forecast caching appear consistent with its purpose, though the review is incomplete and confidence is medium.

The verdict is benign, but that does not mean risk-free. Consider whether you are comfortable with requests to the Open-Meteo API and local forecast caching, and note that the skill does not declare its tool scope. Skillspector inspected only 2 of 5 components fully, with 3 partially inspected, so the evidence is incomplete.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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 (6)

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

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
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 33)May include surrounding context.

md
- `--gaps-file <path>`: a JSON file with a `gaps` array of `{ "local": "HH:MM-HH:MM" }` free
  slots (for example the output of a calendar tool). Outdoor windows are then limited to those slots.
- `A3_LAT`, `A3_LON`, `A3_TZ` environment variables are used when the flags are omitted.
- `DAYBRIEF_API_URL`: forecast endpoint (default `https://api.open-meteo.com/v1/forecast`), for a
  self-hosted Open-Meteo or to rehearse an outage.
- `DAYBRIEF_CACHE_DIR`: where the last good forecast is kept (default: the system temp directory).
  The request is retried up to three times before the cache is used.

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 · scripts/daybrief (reported line 43)May include surrounding context.

text
}

// DAYBRIEF_API_URL: a self-hosted Open-Meteo, or a dead address to rehearse an outage.
const url = new URL(process.env.DAYBRIEF_API_URL || 'https://api.open-meteo.com/v1/forecast');
url.search = new URLSearchParams({
  latitude: String(lat),
  longitude: String(lon),

The module claims to contain pure helpers but performs network requests and persistent filesystem writes.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The module-level documentation at L001 describes these as “Pure helpers,” but fetchJsonRetry performs network requests at L083, and saveForecast creates directories and writes and renames files at L102–L105. These externally observable side effects directly contradict the stated purity rather than merely adding an undocumented implementation detail.

Content

No source excerpt is available for this finding.

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · test/forecast.json (reported line 1)May include surrounding context.

json
"2026-11-16T16:00", "2026-11-16T17:00", "2026-11-16T18:00", "2026-11-16T19:00", "2026-11-16T20:00", "2026-11-16T21:00", "2026-11-16T22:00", "2026-11-16T23:00"], "temperature_2m": [12.0, 12.5, 13.0, 13.5, 14.0, 14.5, 15.0, 15.5, 16.0, 16.5, 17.0, 17.5, 18.0, 18.5, 19.0, 19.5, 19.0, 18.5, 18.0, 17.5, 17.0, 16.5, 16.0, 15.5, 12.0, 12.5, 13.0, 13.5, 14.0, 14.5, 15.0, 15.5, 16.0, 16.5, 17.0, 17.5, 18.0, 18.5, 19.0, 19.5, 19.0, 18.5, 18.0, 17.5, 17.0, 16.5, 16.0, 15.5], "precipitation_probability": [5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 80, 80, 80, 5, 5, 5, 5, 5, 5, 5], "weather_code": [2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 63, 63, 63, 2, 2, 2, 2, 2, 2, 2]}, "daily_units": {"time": "iso8601", "temperature_2m_max": "\u00b0C", "temperature_2m_min": "\u00b0C", "precipitation_probability_max": "%", "weather_code": "wmo code", "sunrise": "iso8601

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · test/forecast.json (reported line 1)May include surrounding context.

json
mperature_2m": [12.0, 12.5, 13.0, 13.5, 14.0, 14.5, 15.0, 15.5, 16.0, 16.5, 17.0, 17.5, 18.0, 18.5, 19.0, 19.5, 19.0, 18.5, 18.0, 17.5, 17.0, 16.5, 16.0, 15.5, 12.0, 12.5, 13.0, 13.5, 14.0, 14.5, 15.0, 15.5, 16.0, 16.5, 17.0, 17.5, 18.0, 18.5, 19.0, 19.5, 19.0, 18.5, 18.0, 17.5, 17.0, 16.5, 16.0, 15.5], "precipitation_probability": [5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 80, 80, 80, 5, 5, 5, 5, 5, 5, 5], "weather_code": [2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 63, 63, 63, 2, 2, 2, 2, 2, 2, 2]}, "daily_units": {"time": "iso8601", "temperature_2m_max": "\u00b0C", "temperature_2m_min": "\u00b0C", "precipitation_probability_max": "%", "weather_code": "wmo code", "sunrise": "iso8601", "sunset": "iso8601"}, "daily": {"time": ["2026-11-15", "2026-11-16"], "temperature_2m_max": [19.0, 19.5], "temperature_2m_min": [12.0, 12.0], "precipitation_proba