hz-psdk-integration
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external files within the user's codebase (e.g., build.gradle, AndroidManifest.xml, and source files) to identify project structure and architecture. It lacks explicit boundary markers or instructions to ignore embedded prompts within these files, creating a surface for indirect prompt injection if the analyzed codebase contains malicious instructions in comments or metadata.
- Ingestion points: SKILL.md (Steps 2.1 through 2.4) reads project configuration and source files.
- Boundary markers: Absent; the agent is instructed to explore the codebase thoroughly without specific delimiters for untrusted content.
- Capability inventory: The skill has access to Bash, Write, and Edit tools, allowing for command execution and file modification based on ingested data.
- Sanitization: No sanitization or validation of the ingested code content is performed before processing.
- [EXTERNAL_DOWNLOADS]: The skill instructions specify the use of the metavr CLI tool for device management and validation, recommending the use of npx -y metavr if the tool is not found on the system path. This results in the download and execution of an external package from the NPM registry at runtime. Given the author is meta-quest, this tool is a vendor-provided resource for Meta Quest development.
Audit Metadata