page-cro
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions and reference tables. It does not include any scripts, automation, or binary files, and does not perform any operations involving the shell or network.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection, but the risk is negligible due to a lack of capabilities:\n
- Ingestion points: Reads local configuration from .agents/product-marketing-context.md or .claude/product-marketing-context.md (SKILL.md).\n
- Boundary markers: Absent; the content is read directly into the agent's context.\n
- Capability inventory: None; the skill provides text-based recommendations only and does not execute tools, commands, or network requests.\n
- Sanitization: Absent; data is processed as natural language context.\n
- Assessment: The absence of any dangerous capabilities prevents exploitation via this ingestion surface.
Audit Metadata