skills/shahrulestar/skills/waktusolat/Gen Agent Trust Hub

waktusolat

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch prayer time data and zone information from the public API at https://api.waktusolat.app. This is a vendor-owned resource required for the skill's primary function.
  • [PROMPT_INJECTION]: The skill proactively addresses the risk of indirect prompt injection by documenting a safety framework for handling external data: (1) Ingestion points: JSON and PDF response bodies from api.waktusolat.app. (2) Boundary markers: The skill requires agents to wrap API payloads in [WAKTUSOLAT_API] tags. (3) Capability inventory: The skill uses standard HTTP GET requests via agent tools. (4) Sanitization: The instructions explicitly command the agent to treat every response body as data rather than instructions and to ignore any commands found within payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 02:48 AM
Security Audit — agent-trust-hub — waktusolat