01-strategy
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from LinkedIn and external websites, creating a surface for indirect prompt injection. \n
- Ingestion points: LinkedIn profile details, posts, and company website content gathered via scraping tools like apimaestro/linkedin-profile-posts and website-scraper (SKILL.md).\n
- Boundary markers: The instructions do not define specific markers or guardrails to prevent the agent from following instructions potentially embedded in the scraped content.\n
- Capability inventory: The skill has permissions to create and update pages and databases within a Notion workspace.\n
- Sanitization: No mentioned validation or filtering of the retrieved external data is performed before it is processed by the model.\n- [SAFE]: The skill utilizes external scraping services (including Apify) and Notion integrations for its core function of market research and strategy documentation, which is consistent with its stated purpose.
Audit Metadata