ux-copywriting-standards

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection attack surface because it interpolates dynamic, potentially untrusted data into user-facing text templates.
  • Ingestion points: Untrusted data enters the agent context through variables such as {filename}, {reason}, {count}, {score}, and {rate} used within the SUCCESS_MESSAGES, ERROR_MESSAGES, and WARNING_MESSAGES templates in SKILL.md.
  • Boundary markers: The skill does not define clear delimiters or include instructions for the agent to treat these variables strictly as data rather than instructions.
  • Capability inventory: The skill has access to file system tools including Read, Edit, Grep, and Glob as specified in the frontmatter.
  • Sanitization: The provided JavaScript implementation examples do not demonstrate any input validation, escaping, or sanitization of the interpolated values.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:15 PM
Security Audit — agent-trust-hub — ux-copywriting-standards