skills/ycs77/skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the mktemp system utility to generate a path for the handoff document. This is a standard and safe operation for creating temporary files.\n- [PROMPT_INJECTION]: Because the skill summarizes conversation history, it possesses an indirect prompt injection surface where malicious instructions in the conversation could influence the summary content.\n
  • Ingestion points: Conversation history and user-supplied arguments are processed for summarization.\n
  • Boundary markers: The instructions do not define specific delimiters to separate untrusted data from instructions.\n
  • Capability inventory: The skill has access to file system writes (temporary files) and shell command execution (mktemp).\n
  • Sanitization: No explicit sanitization or filtering of the summarized content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 03:58 AM
Security Audit — agent-trust-hub — handoff