skills/teachingai/agent-skills/rspack/Gen Agent Trust Hub

rspack

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (HIGH): The automated URLite scanner detected a malicious URL (https://rspack.rs/zh/guide/optimization/profile) within the file examples/guide/optimization/profile.md. Although this appears to be an official documentation link, the blacklist status (UR4703CF1437997CDA-0200) constitutes a critical finding, here adjusted to high-severity as it is associated with the primary purpose of the skill.
  • EXTERNAL_DOWNLOADS (LOW): The skill references and promotes the use of NPM packages (@rspack/core, @rspack/cli) from the web-infra-dev GitHub organization, which is not present in the trusted external sources list. This finding is downgraded to low-severity because it is essential to the primary purpose of the skill.
  • PROMPT_INJECTION (LOW): Surface for indirect prompt injection (Category 8). The skill ingests user queries and provides executable shell command templates without sufficient sanitization or instruction boundary markers. Evidence Chain: 1. Ingestion: User queries in SKILL.md. 2. Boundaries: Missing. 3. Capabilities: Local shell commands (rspack build). 4. Sanitization: None.
  • COMMAND_EXECUTION (LOW): The skill provides standard build and development server commands (e.g., rspack build) intended for local execution by the user.
Recommendations
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:31 PM