rightcode-session-summary-prompt

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is focused on text summarization for conversation handoffs and contains no malicious code, credential exposure, or unauthorized network activity. It uses a structured template to organize the output, which provides inherent boundary markers for the summarized content.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the current conversation history.
  • Ingestion points: Conversation history accessed via the AI agent context as described in SKILL.md.
  • Boundary markers: Employs a structured text template (Objective, Completed, Current verified state, etc.) to organize findings.
  • Capability inventory: No tool usage, subprocess execution, or file-system writing capabilities are defined.
  • Sanitization: No explicit sanitization of the input text is performed, but the risk is mitigated by the lack of executable capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 10:54 AM
Security Audit — agent-trust-hub — rightcode-session-summary-prompt