kai-cro
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from untrusted external sources, including landing pages, signup flows, and competitor funnels from platforms like Meta Ads Library, Google Ads, and TikTok Shop.\n
- Ingestion points: The skill reads local project files (CLAUDE.md, README.md, package.json), local landing page files, and content from external URLs provided by the user or discovered during competitor research.\n
- Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between its own instructions and potentially malicious commands embedded in the external content being analyzed.\n
- Capability inventory: The agent has the capability to read and write files within the project workspace, browse external websites, and execute pre-installed scripts from the Kai environment.\n
- Sanitization: The instructions do not specify any validation, filtering, or escaping of the data retrieved from external sources before it is incorporated into the agent's context for analysis.
Audit Metadata