adapt-materal-enums
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage dependencies and process data.
- Evidence: Use of
pnpm exec,npx, and cleanup commands such asrm -forRemove-Itemfor temporary file management. - [EXTERNAL_DOWNLOADS]: The workflow requires downloading a third-party package from the npm registry.
- Evidence: Installation and execution of
@aptx/frontend-tk-cli, which is the author's specified tool. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it processes untrusted content from a remote API.
- Ingestion points: Data fetched from the user-provided
<base-url>into./tmp/enum-patch.jsonand then read by the agent. - Boundary markers: None present; the instructions do not include delimiters or warnings to ignore instructions embedded in the API data.
- Capability inventory: The skill utilizes subprocess execution via the
aptx-ftCLI and file system modification (read/write/delete). - Sanitization: There is no evidence of sanitization for the
commentorvaluefields before they are passed to the LLM for processing.
Audit Metadata