user-level-detect
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the first three messages of a user session to determine technical proficiency, creating a surface for indirect prompt injection.
- Ingestion points: The skill analyzes the content of the first three messages from the user (
SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the user's messages.
- Capability inventory: No high-risk capabilities such as file system writes, network operations, or shell command execution are present in this skill.
- Sanitization: No sanitization, validation, or filtering of the user-provided text is defined.
Audit Metadata