conversion-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of website URLs and page descriptions provided by users for analysis. This creates a potential surface for indirect prompt injection if an attacker controls the content of a page being audited to influence the agent's output.
- Ingestion points: User-supplied URLs and page descriptions as defined in
SKILL.mdunder Step 1 (รวบรวม page profile). - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions to wrap external content.
- Capability inventory: The skill is capable of generating markdown reports (e.g.,
cro-audit-<page-slug>-YYYY-MM-DD.md). No network operations, arbitrary command execution, or sensitive file access capabilities were found in the provided scripts. - Sanitization: Absent. There is no evidence of filtering or escaping logic for the external content before processing.
Audit Metadata