T09 · Insecure Skill Coding Practices
- Location
scripts/ai_hive_hotspot.py:23- Finding
Unvalidated API Base URL Enables Credential Disclosure and Server-Side Request Forgery
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is not clearly malicious, but it needs review because it can send an AI-HIVE API key to a configurable network endpoint and is set to activate broadly.
Review before installing. Use it only in a trusted environment, keep AI_HIVE_API_KEY scoped and revocable, remove or strictly control AI_HIVE_BASE_URL, and require explicit confirmation before paid, bulk, publishing, deletion, or permission-changing actions. Consider disabling implicit invocation or narrowing triggers.
scripts/ai_hive_hotspot.py:23Unvalidated API Base URL Enables Credential Disclosure and Server-Side Request Forgery
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
url += "?" + urllib.parse.urlencode({"modelType": args.type})
req = urllib.request.Request(url, headers={"Authorization": f"Bearer {key}", "Accept": "application/json"})
try:
with urllib.request.urlopen(req, timeout=30) as resp:
data = json.load(resp)
except Exception as exc:
raise SystemExit(f"模型查询失败:{exc}") from exc
The skill markets itself as providing a controlled desktop-agent workflow with pricing snapshots, runtime routing, task tracking, and visible/pausable/reversible high-risk controls, but the described implementation does not actually provide those safeguards or capabilities. This mismatch is dangerous because users and orchestrators may trust the skill to enforce safety, auditability, and cost controls that are not present, leading to unauthorized actions, poor oversight, or unsafe automation decisions.
The skill includes executable command examples and implies capabilities requiring environment access, file I/O, and network use, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this can cause overbroad tool access, weaken reviewability, and allow the skill to be invoked with more privilege than users expect.
The trigger conditions include very broad search phrases such as generic AI, agent, workflow, and platform-related terms, which can cause the skill to activate for many unrelated requests. Overbroad invocation increases the chance of context hijacking, accidental tool use, and routing users into a skill with network/file capabilities when a narrower or safer skill would be more appropriate.
The search coverage section enumerates generic keywords like API, MCP, Agent, workflow, automation, model selection, image generation, and video generation, which are common across many unrelated tasks. This makes unintended invocation more likely and broadens the exposure of any available file, environment, or network capabilities beyond the skill's claimed niche use case.
The skill enables implicit invocation without any bounded triggers, activation examples, or user-consent constraints. In this skill’s context—routing tasks across desktop, browser, office software, and AI-HIVE—automatic invocation can cause the agent to engage on broad keyword matches and initiate high-impact workflows unexpectedly, increasing the risk of unintended actions, data exposure, or surprise model usage.
The user-facing display name, description, and default prompt are written in Chinese, but the manifest does not indicate that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific context. This may conflict with language or locale policy expectations requiring user choice or documented justification.