Back to skill

Security audit

GEO 内容诊断与优化|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly a disclosed AI-HIVE content and image-generation helper, but its executable client handles API keys, custom endpoints, uploads, downloads, and output files in ways that deserve manual review before installation.

Review this before installing if you will use a real AI-HIVE account. Use only the default trusted AI-HIVE endpoint, do not accept commands that set a custom base URL, keep the API key limited and revocable, upload only files you intend to send to AI-HIVE, and choose a non-sensitive output directory because result filenames and downloads are not strongly constrained.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/imagegen.py:89
Finding

Credential Disclosure and Unrestricted Network Access Through Configurable Endpoints

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/imagegen.py:396
Finding

Arbitrary File Write Through Unsanitized Task Metadata

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
scripts/imagegen.py:7
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The documented behavior understates and mischaracterizes the actual operational scope by omitting generic AI-HIVE capabilities such as model enumeration, chat, video generation, user-info/wallet queries, uploads, and task polling. Undeclared networked and account-scoped actions are security-relevant because they may surprise operators, trigger billable operations, expose account metadata, or broaden the blast radius beyond the claimed GEO/AEO auditing use case.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The documented behavior understates and mischaracterizes the actual operational scope by omitting generic AI-HIVE capabilities such as model enumeration, chat, video generation, user-info/wallet queries, uploads, and task polling. Undeclared networked and account-scoped actions are security-relevant because they may surprise operators, trigger billable operations, expose account metadata, or broaden the blast radius beyond the claimed GEO/AEO auditing use case.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The published skill identity promises GEO/AEO diagnosis and optimization, but the implementation exposes a generic AI Hive image-generation, upload, and task client with a fixed image model. This capability mismatch can mislead operators into granting broader access than intended and allows the skill to be used for unrelated content generation workflows, increasing the risk of policy bypass and unauthorized use under a trusted diagnostic label.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill advertises executable workflows and shell commands that imply access to environment variables, files, network, and local execution, but it does not declare any explicit tool scope or permissions boundaries. This creates an overbroad/implicit capability surface: a host agent may grant more access than users expect, increasing the chance of unintended secret exposure, file access, or network actions when the skill is invoked.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The display name and short description describe a very broad capability spanning workflow design, executable commands, and deliverable content, which overlaps with common writing, SEO, and marketing-help requests. In combination with implicit invocation, this ambiguous scope increases the chance the skill is selected outside its intended context, potentially leading to inappropriate automation or assistance on borderline deceptive promotional tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill enables implicit invocation without any trigger constraints, so it may auto-activate on broad, ordinary content requests that only partially match its purpose. Because this skill can generate runnable workflows and AI-HIVE commands for marketing and content operations, unintended activation could cause overbroad tool use, user confusion, or unsafe assistance in adjacent high-risk content scenarios.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill's exposed generate pathway forwards arbitrary prompts to a remote image-generation API even though the surrounding skill context is framed as GEO content diagnosis. That disconnect makes the tool easier to repurpose for general image creation, including questionable marketing or misleading asset production, under the cover of a benign-sounding analysis skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This code embeds a Chinese-only skill name/description in natural-language strings, including the module docstring and argparse description, without any indication that users can choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language descriptions and CLI guidance entirely in Chinese, starting from the module docstring and continuing through user-facing help text. Because the skill does not offer any language or locale selection or document a justified locale restriction, it can violate a language-choice policy for general-purpose skills.

Content

No source excerpt is available for this finding.