ecmascript-modernization
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies modernization opportunities by reading untrusted external inputs from a codebase.
- Ingestion points: In
references/codebase-audit.md, the agent is instructed to readpackage.json,tsconfig.json, deployment docs, and all project source code usingrg(ripgrep). - Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions embedded in the processed source code or comments.
- Capability inventory: The skill requires the agent to read files, perform complex regex searches via ripgrep, and apply code modifications to the project.
- Sanitization: No sanitization or filtering protocols are mentioned for the content retrieved from the files being modernized.
Audit Metadata