cro
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external content from marketing pages, landing pages, and forms provided via user-supplied URLs. This creates a vulnerability surface where malicious instructions embedded in the external content (e.g., hidden in HTML comments or text) could attempt to influence the agent's output.
- Ingestion points: External web page content accessed via URLs in the user prompt (SKILL.md).
- Boundary markers: The instructions do not include specific delimiters or 'ignore embedded instructions' directives for handling the external content.
- Capability inventory: The skill provides textual analysis and strategic recommendations; it does not define direct command execution, file writing, or network exfiltration capabilities within its own logic.
- Sanitization: No evidence of input sanitization or content filtering is present in the provided instructions.
Audit Metadata