app-store-review-rejections
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of App Store Review rejection notices and Resolution Center messages. This creates a vulnerability surface where malicious or unexpected instructions embedded in these external communications could attempt to influence the agent's logic or downstream tasks.
- Ingestion points: The skill specifically instructs the agent to read and map Guideline violations from Resolution Center messages cited in SKILL.md.
- Boundary markers: There are no specific instructions or delimiters provided to help the agent distinguish between the descriptive content of a rejection message and potential embedded instructions.
- Capability inventory: The skill instructions involve coordinating with sibling tools such as asc-api-automation, which has the capability to perform authenticated network operations and modify application metadata through the App Store Connect API.
- Sanitization: The skill does not define validation or sanitization protocols for the text processed from external developer messages.
Audit Metadata