skills/sidkh/skills/docs-quiz/Gen Agent Trust Hub

docs-quiz

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as credential theft, remote code execution, or persistence mechanisms were detected. The skill's behavior is limited to text-based quiz interactions.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting data from external documentation sources.\n
  • Ingestion points: Documentation is retrieved based on user-provided technology names as per SKILL.md and agents/openai.yaml instructions.\n
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the retrieved documentation.\n
  • Capability inventory: The skill is limited to text generation for quiz questions and feedback. It has no tool-use capabilities for file system access, command execution, or network requests beyond data retrieval.\n
  • Sanitization: There is no explicit sanitization or validation of the content retrieved from documentation sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 08:46 PM