build-mtng-tools-vue
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests requirements from
./spec/README.mdto guide component generation, creating a surface where malicious instructions in the spec file could influence agent behavior. - Ingestion points:
./spec/README.mdreferenced inSKILL.md. - Boundary markers: Absent; the skill lacks delimiters or warnings to ignore embedded instructions in the specification file.
- Capability inventory: The skill is designed to build Vue components/composables and update local files.
- Sanitization: No sanitization or validation of the input specification content is defined.
Audit Metadata