speak-upgrade-migration
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes dynamic context injection (
!command) inSKILL.mdto runnpm list, allowing the agent to check the environment state during initialization. It also instructs the user or agent to run validation commands likenpm testandnode -eto confirm compatibility. - [EXTERNAL_DOWNLOADS]: The skill includes instructions to download and update the
@speak/language-sdkfrom the npm registry. These operations target the official package for the Speak language learning service. - [PROMPT_INJECTION]: The skill includes a file-migration script that creates an indirect prompt injection surface by processing project source code.
- Ingestion points: Reads files with
.ts,.tsx,.js, and.jsxextensions from the./srcdirectory. - Boundary markers: No delimiters or instructions to ignore embedded code are used during the file read/write process.
- Capability inventory: The agent is granted
Write,Edit, andBashcapabilities to perform file modifications and install packages. - Sanitization: The migration script performs direct string replacements based on fixed regex patterns and does not validate the content of the files being modified.
Audit Metadata