ss-pattern
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions and local project files without explicit sanitization or boundary markers, which is a common pattern for UI generation agents.
- Ingestion points: The skill ingests untrusted data from user arguments ($0, $ARGUMENTS) and local project files such as .styleseed/project.json and .styleseed/artifacts/index.json.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the instructions.
- Capability inventory: The skill utilizes powerful tools including Read, Write, Edit, Grep, Glob, and Bash.
- Sanitization: There is no evidence of input validation or content filtering for the data ingested from files or user prompts.
- [COMMAND_EXECUTION]: The skill is configured with Bash access and references the execution of a scoring tool (/ss-score). While these are functional requirements for its UI generation task, the use of shell commands creates a potential attack surface if the agent is manipulated via the ingestion points mentioned above.
Audit Metadata