selaras
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation, component contracts, and Vue examples from the selarasui.my.id domain to inform the agent's code generation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Markdown documentation from a remote source, which establishes a potential surface for indirect prompt injection.
- Ingestion points: Markdown guides and documentation indices retrieved from selarasui.my.id as instructed in SKILL.md.
- Boundary markers: Absent; the instructions do not provide specific delimiters or warnings to ignore instructions within the external documentation.
- Capability inventory: The skill allows the agent to generate Vue components and modify project-specific Nuxt configuration files.
- Sanitization: Absent; there is no mention of sanitizing or validating the content retrieved from the external domain before processing.
Audit Metadata