hmos-arkts-deprecated-interface-checker
Warn
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions to install the
@deveco-codegenie/mcp@betapackage from the npm registry. This constitutes a dependency on external, third-party code. - [REMOTE_CODE_EXECUTION]: The recommended installation command (
npx -y @deveco-codegenie/mcp@beta) downloads and executes code from a remote source, which could be exploited if the package or registry is compromised. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted project data.
- Ingestion points: The skill reads all
.etsfiles and configuration files likebuild-profile.json5within the user's workspace using glob patterns. - Boundary markers: There are no explicit markers or instructions to the agent to treat file content strictly as data and ignore any embedded natural language instructions.
- Capability inventory: The skill uses tools to perform static analysis (
mcp_check_ets_files), builds projects (mcp_build_project), and searches documentation. - Sanitization: No sanitization, escaping, or validation of the file contents is performed before they are ingested into the agent context.
Audit Metadata