find-animation-opportunities
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted third-party source code (SwiftUI and UIKit files) to provide its report. Malicious instructions embedded within the codebase being audited, such as inside comments or string literals, could potentially influence the agent's behavior or findings.
- Ingestion points: The skill reads local iOS source files to identify animation APIs and state changes (Steps 1, 2, and 3).
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the code being analyzed.
- Capability inventory: The agent has permissions to read the local filesystem and execute tool calls (
60fps_search_shots) to an external reference library. - Sanitization: No sanitization or escaping of the ingested code content is described in the skill instructions.
Audit Metadata