Back to skill

Security audit

seedancer

Security checks for vulnerabilities and agentic risk

Overview

Seedancer is a large AI video prompt-planning workflow with disclosed project files, optional calculators, and guarded external-upload guidance, not a hidden or destructive skill.

Install only if you want a structured AI film-production workflow, not just a lightweight prompt template. Before letting an agent use it with files or external services, confirm the project directory, generated deliverable paths, target platform, upload contents, and retention/deletion terms for any real-person media.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (77)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

This finding goes beyond mere mismatch by indicating temporary filesystem copying/mutation and subprocess execution not reflected in the declared purpose. Hidden or under-disclosed file mutation and subprocess behavior can lead to integrity risks, especially if an agent enables these capabilities automatically under the assumption the skill is prompt-only.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This finding goes beyond mere mismatch by indicating temporary filesystem copying/mutation and subprocess execution not reflected in the declared purpose. Hidden or under-disclosed file mutation and subprocess behavior can lead to integrity risks, especially if an agent enables these capabilities automatically under the assumption the skill is prompt-only.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This finding goes beyond mere mismatch by indicating temporary filesystem copying/mutation and subprocess execution not reflected in the declared purpose. Hidden or under-disclosed file mutation and subprocess behavior can lead to integrity risks, especially if an agent enables these capabilities automatically under the assumption the skill is prompt-only.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This finding goes beyond mere mismatch by indicating temporary filesystem copying/mutation and subprocess execution not reflected in the declared purpose. Hidden or under-disclosed file mutation and subprocess behavior can lead to integrity risks, especially if an agent enables these capabilities automatically under the assumption the skill is prompt-only.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 192)May include surrounding context.

md
**机算复核**:`./SKILL.sh dialogue "原台词" --pace slow` 或 `./SKILL.sh check-group --model <模型> --duration <秒> --line "…"`;规划取区间上界,结果与本节公式不一致时以本节为准并修脚本。

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 268)May include surrounding context.

md
**机算复核**:`./SKILL.sh dialogue "原台词" --pace slow` 或 `./SKILL.sh check-group --model <模型> --duration <秒> --line "…"`;规划取区间上界,结果与本节公式不一致时以本节为准并修脚本。

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 367)May include surrounding context.

完整规则:references/output-format.md

完整文件顺序(区块名逐字使用)

markdown

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 367)May include surrounding context.

完整规则:references/output-format.md

完整文件顺序(区块名逐字使用)

markdown

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

This markdown file includes natural-language requirements in the QA section such as '错误语言' and '语言/音色/口型同步', which indicates the skill checks for and may reject outputs based on language constraints. In this file, there is no visible statement that the user can choose the language/locale or opt in to a specific language policy, so the language requirement appears mandatory rather than user-directed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The file title and all operational guidance are written in Chinese, effectively forcing a specific language for users or maintainers interacting with this skill artifact. The document does not provide an opt-in choice, bilingual alternative, or a documented region-specific justification for the locale restriction.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill describes or references shell execution, file reads, and file writes, but does not declare any explicit tool scope or allowed-tools boundary. That creates an authorization ambiguity where a host agent may grant broader capabilities than users expect, increasing the chance of unintended command execution or filesystem modification.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest says the skill only produces prompts and plans, while the body describes generation execution, upload handling, polling, and post-generation workflows. That mismatch expands the operational scope into external service interaction and data transfer, which can expose user assets or trigger actions users did not reasonably expect from a planning-only skill.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

Automatic writes to manifests and delivery outputs exceed the stated prompt-only behavior and create integrity and privacy risks if project files are modified without clear consent. In an agent environment, undocumented writes can overwrite user work, leak sensitive project structure, or create deceptive records of actions taken.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is written entirely in Chinese and does not indicate any user language choice or locale flexibility. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file is a Chinese-language README variant and the language toggle marks Chinese as the active view, but the document itself does not state that Chinese output is optional or user-selected. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file uses prescriptive Chinese-language instructions and labels throughout, including the title and maintenance rules, without indicating that the language requirement is optional or region-specific. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The opening lines explicitly state that the document is available in Chinese only. This is a natural-language locale policy constraint that does not offer the user a language choice or opt-in within the skill file itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The opening notice states that the document is available in Chinese only, with only an English overview elsewhere. This is a natural-language locale policy constraint that forces a specific language rather than offering the user a choice or opt-in within the skill documentation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file explicitly states that the document is available in Chinese only, with only an English overview elsewhere. This imposes a language constraint in the skill documentation without user opt-in or a stated region-specific justification, matching the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document explicitly states that it is available in Chinese only, with only an English overview elsewhere. This imposes a language constraint in the skill documentation without offering the user a language choice or documenting a justified locale-specific requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file explicitly states that the document is available in Chinese only, with only an English overview elsewhere. This is a natural-language locale policy constraint presented without user opt-in or a clear region-specific justification, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The opening notice states that the document is available in Chinese only, with only an English overview elsewhere. This imposes a specific language on users without offering a choice or documenting an opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The opening notice states that the document is available in Chinese only, with only an English overview elsewhere. This imposes a specific language on users without offering a choice or opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The opening lines state that the document is available in Chinese only, with only an English overview elsewhere. This imposes a language constraint in the skill documentation without offering the user a choice or opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The opening notice states that the document is available in Chinese only, with only an English overview elsewhere. This imposes a language constraint without presenting a user language choice or documenting a justified locale-specific requirement, which matches the policy-violation criteria for forced language or locale.

Content

No source excerpt is available for this finding.