deprecate-cds-api
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes symbol names, replacement descriptions, and version tags provided by the user or found within the repository's source files.
- Ingestion points: User-provided arguments for symbol names and replacement text, as well as symbol exports discovered via
GrepinSKILL.md. - Boundary markers: There are no explicit instructions to use delimiters or sanitization when interpolating these external strings into JSDoc comments or JSON metadata files.
- Capability inventory: The skill has the ability to read and modify local files (
StrReplace) and execute shell commands (Bash(yarn nx run:*)) for linting. - Sanitization: No validation or escaping of the user-provided strings is mentioned before they are written to the codebase.
Audit Metadata