expo-ui-jetpack-compose
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructs the user to install the official
@expo/uipackage from the Expo organization, which is a well-known and trusted provider in the developer community. - [SAFE]: All external URLs and resources, including documentation links to
docs.expo.devand Material Symbols fromfonts.google.com, target trusted and well-known services. - [INDIRECT_PROMPT_INJECTION]: The skill encourages documentation lookups by interpolating component names into a URL template (
docs.expo.dev/.../{component-name}/index.md). While this creates a theoretical surface for indirect prompt injection, it is considered safe due to the trusted target domain and read-only purpose. 1. Ingestion points: The{component-name}placeholder in documentation URLs. 2. Boundary markers: None. 3. Capability inventory: Fetching external documentation from a trusted source. 4. Sanitization: None. - [METADATA_POISONING]: The YAML frontmatter includes a
risk: criticaltag. Although this contradicts the benign nature of the skill's instructions, it appears to be a metadata error rather than a deceptive or malicious injection attempt.
Audit Metadata