ios-hig-design
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains inconsistent metadata in SKILL.md where instructions, examples, and error-handling tables refer to 'ORM configuration' and 'ORM authentication' instead of iOS design principles. While likely a clerical error, this deceptive metadata misrepresents the skill's operational context.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests user-provided requirements to generate code and design recommendations without adequate isolation.
- Ingestion points: User requirements and constraints mentioned in the 'Instructions' section of SKILL.md.
- Boundary markers: Absent; the skill does not use delimiters or instructions to distinguish user data from the system prompt.
- Capability inventory: The skill utilizes Read, Glob, and Grep tools as specified in the allowed-tools field in SKILL.md, though it lacks the Write tool needed to fulfill its stated purpose of applying code changes.
- Sanitization: Absent; there is no validation or filtering of user-supplied input before it is processed.
Audit Metadata