metadata-optimizer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external source code from the project, which introduces a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: File content from
app/,pages/, andcomponents/directories are scanned as defined in theSKILL.mdworkflow. - Boundary markers: The instructions do not specify any delimiters or warnings to ignore potential instructions embedded within the metadata strings being analyzed.
- Capability inventory: The skill is limited to the
Read,Grep, andGlobtools, lacking any network access, file writing, or shell execution capabilities. - Sanitization: No sanitization or escaping of the extracted metadata content is described.
- [SAFE]: The skill uses a minimal and appropriate set of tools to perform its stated primary function of SEO analysis. It does not attempt to access sensitive system files or establish network connections.
Audit Metadata