pages-features
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and templates for content generation and does not include any scripts, commands, or external dependencies.
- [PROMPT_INJECTION]: The skill instructs the agent to read local project files such as
.claude/product-marketing-context.mdto gather context. This creates an attack surface for indirect prompt injection from untrusted content in those files. - [PROMPT_INJECTION]: Evidence Chain: 1. Ingestion points: File reads of
.claude/product-marketing-context.mdand.cursor/product-marketing-context.md. 2. Boundary markers: Absent. 3. Capability inventory: None; the skill is restricted to generating text and metadata. 4. Sanitization: Absent.
Audit Metadata