Skills
Navigate
skills/jeffallan/claude-skills/react-native-expert/Gen Agent Trust Hub

react-native-expert

Fail

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates a development workflow that involves executing shell commands based on project requirements.
  • Ingestion points: User-provided application requirements and implementation requests (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt templates.
  • Capability inventory: The skill instructs the agent to run commands such as npx expo doctor, npx expo run:ios, npx expo run:android, and adb logcat (SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation of user-provided inputs before they are incorporated into suggested command executions.
  • [EXTERNAL_DOWNLOADS]: The skill contains links to external documentation hosted at jeffallan.github.io.
  • Evidence: Documentation (https://jeffallan.github.io/claude-skills/skills/frontend/react-native-expert/) (SKILL.md).
  • Context: The resource belongs to the skill's author and serves as a legitimate technical reference for the skill's domain.
  • [COMMAND_EXECUTION]: The skill workflow incorporates several CLI tools for environment verification and native platform builds.
  • Evidence: Commands such as npx expo doctor, npx expo run:ios, npx expo run:android, and npx expo install <module> are documented for use during error recovery and setup phases (SKILL.md).
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Oct 3, 2026, 03:43 PM