ss-pattern
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from both user input and local project configuration files, creating a surface for indirect prompt injection.
- Ingestion points: User-provided description ($ARGUMENTS) and project configuration files located in the
.styleseed/directory (e.g.,project.json,artifacts/index.json,manifests/*.json) as referenced inSKILL.md. - Boundary markers: Absent. There are no explicit instructions or delimiters to ensure the agent ignores potential instructions embedded within the configuration files or user descriptions.
- Capability inventory: The skill has access to powerful tools including
Bash,Write, andEdit, which could be exploited if malicious instructions are successfully injected via the ingestion points. - Sanitization: The skill does not perform any validation, filtering, or escaping of the content read from the configuration files before using it to compose UI components.
Audit Metadata