mobile-monorepo-ios
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the local repository (such as
package.json,app.json, and lockfiles) to determine project configuration and automate workflows. - Ingestion points: Environment detection logic in
SKILL.mdand repository inspection commands inreferences/architecture-choice.md. - Boundary markers: There are no explicit instruction-isolation markers or "ignore embedded instructions" warnings when the agent reads these external configuration files.
- Capability inventory: The agent has the authority to execute powerful build and release commands (including
xcodebuild,adb, andeas-cli) and modify files within the target repository. - Sanitization: No explicit sanitization, validation, or escaping of the configuration file content is performed before it is processed by the agent.
Audit Metadata