tailwind-class-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's design facilitates the processing of external, potentially untrusted user data, which serves as a vector for indirect prompt injection if the inputs contain instructions intended to override agent behavior.
- Ingestion points: Untrusted data enters the agent context via user requests containing Tailwind class patterns, React/Vue code, and other frontend development snippets as described in the overview and activating triggers (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate user-supplied class strings from the skill's operational logic, increasing the risk of the agent following instructions embedded within the data.
- Capability inventory: The skill has access to sensitive tools including
Bash(cmd:*),Write, andEdit, which allow for shell command execution and file modification (SKILL.md frontmatter). - Sanitization: There is no mention of sanitization, validation, or escaping of user-provided class strings or code before they are processed by the agent's optimization logic.
Audit Metadata