prompt-master
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to wrap user-provided information into XML structures for prompt refinement.
- Ingestion points: User input is ingested into tags such as <user_prompt>, , and as described in SKILL.md.
- Boundary markers: The skill uses XML tags for data delimitation, which is a defensive measure but can be defeated by malicious input that escapes the tags.
- Capability inventory: No executable code, subprocesses, or external communication capabilities are present in the skill files.
- Sanitization: No sanitization or escaping of control characters in user input is specified.
Audit Metadata