ux-writing
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional and provides guidelines for user interface copywriting. It does not include any executable code, remote script downloads, or network operations.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it is designed to ingest and process data from a local research corpus located at ~/jtbd/jtbd.json. This is a legitimate function for the skill's purpose of grounding copy in research evidence. 1. Ingestion points: ~/jtbd/slug/jtbd.json in SKILL.md. 2. Boundary markers: No specific delimiters are used when incorporating quotes from the corpus. 3. Capability inventory: The skill is focused on text generation and microcopy review. 4. Sanitization: No explicit sanitization or filtering of the corpus data is described. The risk is evaluated as safe because the ingestion is limited to local research files and the output is intended for human-facing interface text.
Audit Metadata