session-handoff

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's functionality is limited to analyzing current conversation history and formatting it into a summary prompt. It does not perform file system writes, network requests, or command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection because it processes untrusted user input from the session history.
  • Ingestion points: The skill reads the entire current session context to create a summary.
  • Boundary markers: While it uses structured markdown headers for the output, it does not explicitly instruct the recipient agent to ignore or delimit potentially malicious instructions within the distilled context.
  • Capability inventory: The skill does not utilize any high-risk capabilities such as eval(), subprocess calls, or network requests.
  • Sanitization: No explicit sanitization or escaping of the ingested conversation history is performed.
  • Note: This vulnerability surface is inherent to the skill's primary purpose of context management and is considered a low risk in this specific implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 05:22 PM