storekit
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
SKILL.mdfile instructs the agent to fetch additional documentation fromsosumi.ai, an unofficial third-party Markdown mirror of Apple's developer documentation. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted data from an external source:
- Ingestion points: External documentation content is fetched from
sosumi.aiURLs (SKILL.md). - Boundary markers: The instructions do not define delimiters or "ignore embedded instructions" warnings for the fetched content.
- Capability inventory: The ingested data informs the agent's understanding of StoreKit APIs, which is used to generate responses and technical guidance.
- Sanitization: There is no specified logic for sanitizing or validating the external documentation content before it enters the agent context.
Audit Metadata