digits-fintech-swiss-template
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided copy and metric values to populate a pre-defined HTML template. While the output is wrapped in a defined artifact identifier, there are no instructions for the agent to sanitize or validate the untrusted user input before placing it into the HTML structure, which could lead to script injection if malicious content is provided.
- Ingestion points: User-provided text and metrics mentioned in the workflow section of SKILL.md.
- Boundary markers: Present as tags for the final output, but absent for internal data interpolation within the HTML slides.
- Capability inventory: The skill utilizes file_write to generate the primary index.html artifact.
- Sanitization: Instructions for escaping, filtering, or validating user-supplied data before interpolation are absent.
Audit Metadata