better-prompt
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied task descriptions to generate rewritten prompt instructions.
- Ingestion points: The skill ingests user input via the
triggers: [user]mechanism to perform the rewriting task. - Boundary markers: The skill does not explicitly define delimiters to separate the user's original task from the rewriting instructions, which is common for prompt engineering utilities.
- Capability inventory: There are no dangerous tools, shell commands, file system operations, or network calls identified in the skill configuration or body.
- Sanitization: The skill does not include specific sanitization or escaping logic for the user-provided prompt before processing.
Audit Metadata