page-cro
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) as it processes untrusted external data entered via user-provided URLs, copy, and the .claude/product-marketing-context.md file.
- Ingestion points: Data enters through page URLs, marketing copy (README.md, SKILL.md), and the .claude/product-marketing-context.md context file (SKILL.md).
- Boundary markers: Absent; instructions do not provide delimiters (like XML tags) or directives for the agent to ignore instructions embedded within the analyzed content.
- Capability inventory: No dangerous capabilities such as shell command execution, file-writing, or network-writing tools are identified in the provided skill definition.
- Sanitization: Absent; the skill does not specify any input validation, escaping, or filtering for the external content before processing.
Audit Metadata