iphone-duo-readiness
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze external, untrusted application source code to identify specific patterns (e.g., 'Grep the codebase for these...').
- Ingestion points: The agent is directed to read the deployment target, SDK version, and search through codebase files for specific layout and API calls in
SKILL.md(Step 2). - Boundary markers: There are no instructions provided to treat content within the audited codebase as untrusted or to use specific delimiters to prevent the agent from executing instructions found within the code comments or strings.
- Capability inventory: The skill acts as a router to other specialized tools (e.g.,
iphone-duo-camera,iphone-duo-adaptive-layout) and references local project files, providing a path for instructions found in external data to influence further agent actions. - Sanitization: No sanitization, escaping, or filtering of the external codebase content is mentioned before it is processed by the agent.
Audit Metadata