trigger-agents

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill implements patterns that process untrusted data from various inputs and interpolates them directly into prompts, which could be exploited if the data contains malicious instructions.\n
  • Ingestion points: SKILL.md (tasks: translate-copy, route-question, fact-checker), references/ai-tool.md (task: read-url, web-search).\n
  • Boundary markers: Absent; input strings are used directly in template literals.\n
  • Capability inventory: Network access via fetch and agentic tool-calling capabilities.\n
  • Sanitization: No input validation or instruction-filtering is present in the templates.\n- [SAFE] (SAFE): Legitimate framework usage. The skill accurately demonstrates the use of @trigger.dev/sdk for durable execution and task orchestration. Dependencies used are reputable and consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:48 PM