state-machine
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes component source code and data hooks to identify rendering states, creating an entry point for untrusted data from the project to influence agent behavior.
- Ingestion points: The agent reads component files and data hooks in the project directory as described in Step 2 ('Find the states in the code') of
SKILL.md. - Boundary markers: No explicit boundary markers or instructions to disregard instructions embedded in code comments are provided when the agent is directed to read the component code.
- Capability inventory: The skill requires the ability to create new files and directories for scratch routes (Step 3 in
SKILL.md) and delete them upon completion ('Remove it in one step, on the user's word' inSKILL.md). - Sanitization: No sanitization or validation logic is specified for the content read from the project files before it is used to determine the list of states or build fixtures.
Audit Metadata