homepage-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external project context files to gather information about the product and audience. This ingestion of untrusted local data could potentially be used to influence agent behavior if the target files contain malicious instructions.
- Ingestion points: The skill references
.claude/project-context.mdand.cursor/project-context.mdin the 'Initial Assessment' section ofSKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the content read from these files.
- Capability inventory: The skill's primary capabilities are limited to generating text, SEO metadata, and site structures. No command execution or network operations are present in the skill.
- Sanitization: No sanitization or validation of the ingested context file content is performed.
Audit Metadata