cro
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data from marketing pages, forms, and user-provided URLs.
- Ingestion points:
SKILL.mdexplicitly instructs the agent to analyze marketing pages, landing pages, and lead capture forms when a user shares a URL or asks for feedback. - Boundary markers: Absent. The instructions do not define specific delimiters or provide warnings to the agent to ignore instructions that might be hidden within the HTML or content of the analyzed pages.
- Capability inventory: The skill is restricted to analytical and advisory tasks. No file system modifications, subprocess executions, or network exfiltration patterns are present in the provided files.
- Sanitization: Absent. The skill does not mention any sanitization or filtering of external content before processing it for analysis.
Audit Metadata