html-preview
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external REST API (including item titles, notes, and IDs) and a local configuration file, establishing an attack surface for indirect prompt injection.
- Ingestion points: Data is ingested from the user-provided API service via various GET endpoints and from the local
~/.config/html-preview/config.yamlfile. - Boundary markers: The skill lacks explicit instructions for the agent to use boundary markers or to ignore instructions embedded within the API responses.
- Capability inventory: The skill instructs the agent to execute shell commands (
curl) for network operations and file uploads, using data interpolated from the API and configuration. - Sanitization: There are no specified procedures for validating or sanitizing the content retrieved from the external service before it is used to construct commands.
Audit Metadata