tui-sticky
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists solely of markdown instructions, JSON schemas, and text-based examples. It does not include any executable scripts, binaries, or configuration files that perform active operations.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an input model that ingests untrusted data to produce design specifications. * Ingestion points: The Input Model JSON structure defined in SKILL.md receives data at runtime. * Boundary markers: There are no explicit boundary markers or instructions provided to the agent to treat input data as untrusted or to ignore embedded instructions within the input. * Capability inventory: The skill generates PENCIL_BATCH_DESIGN plans consisting of DSL-like function calls (e.g., G(), I(), U()) intended for the Pencil MCP tool. * Sanitization: No sanitization or validation rules are defined for the input data before it is interpolated into the design specifications.
- [SAFE]: Analysis of the instructions shows no attempts at prompt injection, data exfiltration, obfuscation, or persistence. All defined behaviors align with the stated purpose of UI design generation.
Audit Metadata