client-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its core functionality of researching and synthesizing external web content.
- Ingestion points: Phase 1 involves multiple steps (Company Research, Competitor Research, Founder Research via LinkedIn, and Paid Ads Review) that fetch data from external, untrusted sources on the public web.
- Boundary markers: There are no explicit instructions or delimiters defined to separate fetched external content from the agent's internal instructions, nor are there warnings to ignore instructions embedded in research data.
- Capability inventory: The skill primarily writes the synthesized data to local files within a
clients/directory structure. While it does not directly execute code based on the data, the synthesized "Intelligence Package" and "Growth Strategies" could be influenced by malicious content on researched sites. - Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content retrieved from the web before it is analyzed by the agent.
Audit Metadata