add-config-field
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill outlines a legitimate process for maintaining a repository's configuration schema. The use of file manipulation tools (Read, Edit, Glob, Grep) is appropriate for the described task. No credentials, remote execution patterns, or persistence mechanisms were found.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-defined inputs such as field names and default values to update documentation and configuration templates.
- Ingestion points: User-provided inputs (Field name, Default value, Section, Comment, Used by) defined in
SKILL.md. - Boundary markers: None present; user input is interpolated directly into instructions for editing files.
- Capability inventory: Uses the
Edittool to modify multiple repository files. - Sanitization: No explicit sanitization or validation of input data is defined.
- Context: This is a standard surface for a configuration management skill and is not assessed as a malicious finding in this context.
Audit Metadata