affiliate-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read project context files (.claude/project-context.md, .cursor/project-context.md), which represents an ingestion surface for potentially untrusted data. 1. Ingestion points: local project context files. 2. Boundary markers: Not specified. 3. Capability inventory: Textual content generation only. 4. Sanitization: None.
- [SAFE]: The skill is composed of markdown guidelines for copywriting and page design. No executable scripts, network exfiltration, or obfuscation techniques were found.
Audit Metadata