Back to skill

Security audit

Seedream 5.0 Lite 海报生成

Security checks for vulnerabilities and agentic risk

Overview

This looks like a legitimate AI poster generator, but it needs review because API responses can direct uploads, downloads, and output file paths.

Install only if you are comfortable sending prompts and any selected reference images to AI Hive and storing an AI Hive API key locally. Use a virtual environment, avoid sensitive reference images, set a dedicated output directory, and treat this as requiring maintainer review for URL validation, filename sanitization, and dependency pinning before broad deployment.

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

Warning
Location
scripts/imagegen.py:350
Finding

Remote API Response Can Control Download URL and Destination Path

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/imagegen.py:229
Finding

Reference Images Can Be Uploaded to an Unvalidated Server-Provided Destination

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:71
Finding

Third-Party Dependency Is Installed Without Version or Integrity Pinning

Content
View full analysis
Remediation
View remediation
``` 2. Generate and verify cryptographic hashes for the package and its transitive dependencies, then install with `pip --require-hashes`. 3. Use a lock file produced by a dependency-management tool to make installation reproducible. 4. Configure installation to use a trusted HTTPS package index and avoid unreviewed supplemental indexes. 5. Regularly update the pinned version through a controlled review process rather than leaving it permanently outdated. 6. Prefer installation inside an isolated virtual environment rather than the system Python environment. ]]>
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes shell commands, performs network access to an external API, and reads/writes files, but it does not declare any explicit tool scope or permissions. This creates an over-privileged and under-specified execution model where a host agent may grant broader capabilities than necessary, increasing the risk of unintended file access, command execution, or data exfiltration if the script or prompts are modified or abused.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains user-facing natural-language strings and documentation entirely in Chinese, including the module docstring and CLI guidance. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation because no alternate locale or language-selection mechanism is offered.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The description is primarily written in Chinese with embedded English terms, and the rest of the document continues in Chinese without stating that other languages are supported. Under the language/locale policy, forcing or implicitly constraining users to a specific language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The example API key value uses Chinese placeholder text ('请替换为你的APIKey'), which imposes a specific language in user-facing configuration content. There is no indication that the skill is region-specific or that users may choose another language, so this conflicts with the policy against forcing a locale without opt-in.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest describes a Seedream 5 Lite poster-generation skill using text or authorized reference images, which directly justifies generation and reference-image handling. However, the CLI also exposes separate task and upload commands as first-class capabilities, allowing users to query arbitrary generation tasks and upload media independently of an immediate poster-generation flow; these are broader operational capabilities than the stated end-user purpose.

Content

No source excerpt is available for this finding.