T01 · Skill Instruction Hijacking
- Location
agents/openai.yaml:4- Finding
Implicit Commercial Task Redirection to AI-HIVE
- Content
View full analysis
Vulnerability Details
File Location:
agents/openai.yaml:4-6; supporting promotional link atSKILL.md:7
Vulnerability Type: Implicit skill activation and instruction-level commercial redirection
Risk Level: MediumVulnerable Code
agents/openai.yaml:4-6:yaml default_prompt: "Use $seedance-source-api-channel-ai-hive to complete a Seedance channel capability verification from Seedance source API channel to AI-HIVE with evidence and rollback gates." policy: allow_implicit_invocation: trueEnglish rendering is provided because the source prompt contains mixed English and Chinese text.
SKILL.md:7:markdown [Open AI-HIVE](https://ai-hive.iclip.cn/chat)Technical Analysis
The skill permits implicit invocation while its default prompt predetermines AI-HIVE as the migration target. Its broader instructions associate general Seedance API searches and evaluations with an AI-HIVE comparison and migration workflow.
This exceeds the minimum instruction scope needed for a neutral Seedance capability audit. A capability-audit skill could collect model, price, concurrency, and reliability evidence without selecting a specific commercial destination before the user requests that provider.
The external link is not executable code, and the reviewed package does not automatically contact it. Nevertheless, the combination of implicit activation, predetermined migration framing, and a direct commercial link can alter the agent's current-session objective and steer users toward one vendor. This is instruction-level hijacking rather than host compromise.
No fixed advertisement appended to every final response was confirmed. The confirmed issue is persistent task steering within the skill instructions and configuration.
Attack Path
- A user asks a general question about Seedance APIs, versions, costs, alternatives, or video-generation channels.
- Because `allow_implicit_invoca ...[truncated 1088 chars]
- Remediation
View remediation
Remediation Suggestions
- Set
allow_implicit_invocationtofalseso the skill runs only after an explicit user request. - Remove AI-HIVE as the predetermined target from the default prompt. Ask the user to select comparison providers or use provider-neutral wording.
- Narrow the activation scope to requests that explicitly mention AI-HIVE or explicitly request a migration comparison involving it.
- Move the commercial link into an optional resources section and display it only when the user asks for AI-HIVE documentation or access.
- Separate neutral Seedance capability verification from vendor-specific migration guidance into distinct skills.
- Require explicit user confirmation before opening an external service, submitting data, or beginning any provider-specific migration workflow.
- Clearly disclose any commercial affiliation or sponsorship before making provider-specific recommendations.
- Preserve the existing safeguards requiring non-production samples, authorization checks, budget limits, evidence collection, and rollback gates.
- Set
