specialist-engineering-react-native-engineer

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by interpolating user input directly into a sub-agent prompt. 1. Ingestion points: The {the user's question} placeholder in the Agent tool call in SKILL.md. 2. Boundary markers: None identified; user input is not delimited from the system instructions. 3. Capability inventory: The sub-agent is authorized to perform complex software engineering and mobile development tasks. 4. Sanitization: None detected in the skill configuration.
  • [NO_CODE]: The skill does not contain any executable scripts, source code files, or binary executables, relying exclusively on markdown instructions and agent tool definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-engineering-react-native-engineer