Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it claims: it queries GitHub for agent-related repositories and formats a leaderboard, with no hidden persistence or destructive behavior found.
Before installing, note that the script contacts GitHub and may read GITHUB_TOKEN or a --token value, so use a fine-grained, minimal token or run unauthenticated if possible. Expect the default markdown output to include Chinese labels unless the script is customized.
The skill advertises executable usage that relies on environment variables and outbound network access, but the manifest does not declare any tool scope or permission boundaries. In an agent environment, this can cause the skill to be invoked with broader capabilities than intended, increasing the chance of unreviewed network access and credential exposure via environment variables.
The activation text says to use the skill when the user asks for "GitHub agent trends, AI agent leaderboard, coding agents, or popular agent frameworks on GitHub." Phrases like "coding agents" and "popular agent frameworks on GitHub" are broad and lack negative examples or narrower constraints, which could cause unintended invocation for general discussion requests rather than explicit leaderboard generation.
This Python file hard-codes Chinese locale output via period labels such as "日榜/周榜/月榜", and the generated report text later uses Chinese UI strings. The policy explicitly calls for flagging language or locale constraints when a skill forces a specific language without offering user choice or documenting a justified regional scope.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
params = urllib.parse.urlencode({
"q": query, "sort": sort, "order": order, "per_page": per_page
})
url = f"https://api.github.com/search/repositories?{params}"
headers = {"Accept": "application/vnd.github+json", "User-Agent": UA}
if token:
headers["Authorization"] = f"Bearer {token}"
The formatted output uses Chinese phrases like "GitHub Agent 趋势榜" and "生成时间" directly in user-facing text. Because the file provides no opt-in, locale flag, or documented region-specific justification, this is a natural-language policy violation under the language/locale rule.
The skill instructs users to export a GitHub token and pass it to a script without any warning about token scope, storage, or safe handling. This creates a realistic risk of users supplying overly privileged credentials or exposing tokens through shell history, logs, screenshots, or inherited process environments.
No suspicious patterns detected.