upgrade-react-native
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection via the consumption of external documentation.
- Ingestion points: In step 7 of
SKILL.md, the skill fetches third-party library README files from external GitHub repositories or npm pages to check for version compatibility. - Boundary markers: No specific boundary markers or isolation instructions are provided to prevent the agent from obeying instructions embedded inside those external README files.
- Capability inventory: The skill has the capability to write and modify local project files, including
package.json, native Android/iOS files, and configuration files. - Sanitization: There is no automated validation or sanitization applied to the retrieved README content before it is parsed by the model.
- [EXTERNAL_DOWNLOADS]: The skill downloads release metadata and unified diff files from the
react-native-community/rn-diff-purgerepository and alternative platform diffs fromacoates-ms/rnw-diffto identify and apply required codebase changes.
Audit Metadata