Skills
skills/workshop-ventures/skills/backend-ai-agent/Gen Agent Trust Hub

backend-ai-agent

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill contains examples vulnerable to Indirect Prompt Injection. Evidence:
  • Ingestion points: The generateSummary function in SKILL.md and the ask method in references/agent-patterns.md ingest raw user data.
  • Boundary markers: The prompt template in SKILL.md directly interpolates ${content} without using XML-style delimiters or 'ignore embedded instructions' markers.
  • Capability inventory: The agent implementation in references/agent-patterns.md provides tools like createTask and searchDocuments which could be triggered maliciously via injected content.
  • Sanitization: No sanitization, escaping, or validation of user-provided strings is present in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM