new-feature
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes a feature name as a user-invocable argument and uses it to generate directory structures and source files.\n
- Ingestion points: The feature name is captured via the $ARGUMENTS variable in SKILL.md.\n
- Boundary markers: The skill does not employ delimiters or instructions to ignore potential commands embedded within the feature name argument.\n
- Capability inventory: The skill uses Write, Read, and Glob tools to create and manage files across the project structure (src/app, src/domain, etc.).\n
- Sanitization: There is no evidence of validation or sanitization to prevent the use of malicious strings (such as directory traversal patterns) in the feature name.
Audit Metadata