contact-page-generator
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill attempts to read project context files (
.claude/project-context.mdor.cursor/project-context.md) to align with brand voice. While this is an ingestion point for potentially untrusted data, the skill lacks any dangerous capabilities (such as network access or command execution) that could be exploited via an injection attack. This is a standard feature for AI assistant integration. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns, external script downloads, or dynamic code evaluation were found.
- [DATA_EXFILTRATION]: No network operations or unauthorized data transfer mechanisms are present in the skill.
- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override agent behavior.
- [OBFUSCATION]: No obfuscated content, encoded strings, or hidden characters were detected.
Audit Metadata