landing-page-cro-expert
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources, which is a common vector for indirect prompt injection.
- Ingestion points: The skill instructions in
SKILL.mdspecify that it should be used when a user "pastes a URL or screenshot" of a landing page for auditing. - Boundary markers: The instructions do not include specific delimiters or guidelines for the agent to differentiate between the user's audit request and potentially malicious instructions embedded within the landing page text itself.
- Capability inventory: The skill performs text analysis, scoring, and copy generation. No system-level commands, file writes, or network exfiltration tools are utilized in the provided instructions.
- Sanitization: There is no mention of sanitizing or filtering the content retrieved from URLs before it is processed by the agent.
Audit Metadata