upload-element-previews
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
bun run upload-element-preview. This is used to trigger a local script within thepackages/docsdirectory to process and upload assets. - [DATA_EXFILTRATION]: The skill is designed to upload local preview assets from
.element-previewsorstatic/elementsto an external domainremotion.media. This domain is a known resource associated with the vendor 'remotion-dev' and is used for hosting project-specific media. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied or project-derived data (element slugs and categories) which are then interpolated directly into a shell command line.
- Ingestion points: The 'Element slug' identified in step 1 of the instructions.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are provided for the input slug.
- Capability inventory: The skill possesses the capability to execute shell commands (
bun run), delete local files (rmvia instruction 5), and perform Git operations (commitandpush). - Sanitization: The instructions do not specify sanitization or validation logic for the slug input before it is used in the
buncommand.
Audit Metadata