find-skills-ja
Warn
Audited by Snyk on Aug 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). 指定ワークフローは Step 4 で「候補となった上位1〜2件」のSKILL.md(https://skills.sh///)を取得して読み、危険な指示の有無を検証するが、これはアウトサイダーが自由文を投稿して直接投入できる種類の入力(メール/チケット/任意URL等)を監視・消費するものではなく、スキルの作者リポジトリ側の第一級コンテンツ(SKILL.md)を選択的に取得する前提の手順であるため、外部からの間接プロンプト注入としては限定的。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at runtime to fetch SKILL.md from https://skills.sh/// (example: https://skills.sh/github/awesome-copilot/meeting-minutes) to read instructions that directly control the agent's behavior, and the workflow also calls npx (which executes remote "skills" code), so remote content is fetched and used to control prompts.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata