skill-competitor-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external social media platforms (Xiaohongshu, Douyin, Bilibili, etc.) using
web_fetchandweb_searchto analyze competitor accounts and user comments. - Ingestion points: Competitive account profile information, post content, and user comments are fetched at runtime in
SKILL.md(Step 2, 3, and 6) and defined inreferences/data-collection.md. - Boundary markers: The instructions do not specify explicit delimiters or "ignore embedded instructions" warnings for the fetched external content.
- Capability inventory: The skill utilizes network-enabled tools (
web_fetch,web_search) and instructions to process and summarize external data. - Sanitization: No sanitization or filtering of the external content is described before it is processed by the agent's logic.
Audit Metadata