motion-design-rules
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to run
@helios-project/clivianpx. This fetches the package from the NPM registry at runtime. The use of the@latesttag means the executed code is not pinned to a specific version, which is a common but sub-optimal security practice for supply chain integrity. - [COMMAND_EXECUTION]: The instructions require the agent to execute shell commands (e.g.,
npx,helios verify,helios check) to perform technical validations on media assets and code. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data, creating a surface for indirect prompt injection.
- Ingestion points: Processes user-supplied files including
track.mp3,page.html, andlyrics.srt(referenced inSKILL.md). - Boundary markers: There are no explicit instructions for the agent to use delimiters or to ignore potential instructions embedded within the metadata or content of these processed files.
- Capability inventory: The skill uses shell tools (
npx,helios) to interact with the file system and network (via package download) based on these inputs. - Sanitization: The skill does not describe any sanitization or validation steps for the content of the ingested files before processing.
Audit Metadata