core-haptics

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined interaction intents and requirements to generate or review Swift implementation code.
  • Ingestion points: Interaction intent and non-haptic fallback definitions provided by the user (refer to Implementation Workflow in SKILL.md and evals/evals.json).
  • Boundary markers: The instructions lack explicit guidance for the agent to use delimiters or ignore potentially malicious instructions embedded within user-provided intent strings.
  • Capability inventory: The skill facilitates the generation of Swift code utilizing the CoreHaptics system framework.
  • Sanitization: There are no specified mechanisms for escaping or validating the content of external interaction descriptions before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:13 AM
Security Audit — agent-trust-hub — core-haptics