transitions-dev
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection due to its analysis of untrusted workspace content.
- Ingestion points: The
transitions reviewandtransitions refinecommands (defined inSKILL.md) instruct the agent to read and analyze various project files (CSS, JS, JSX, TSX) to identify animation patterns and hardcoded timing values. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential natural language directives that might be embedded within comments or strings in the analyzed code.
- Capability inventory: The
transitions applycommand provides the agent with the ability to write new CSS and JavaScript code into the user's workspace, creating a link between data ingestion and file system modification. - Sanitization: There is no evidence of filtering or sanitization being performed on the code content read from the project before it is used to influence the agent's suggestions or modifications.
Audit Metadata