skills/yikart/aitoearn/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute the mktemp command to generate a unique file path for saving the handoff document.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it summarizes user-controlled conversation data into a file. Ingestion points: Processes the current conversation history and user-supplied arguments as described in SKILL.md. Boundary markers: No delimiters or instructions are specified to prevent the agent from following instructions embedded within the conversation history. Capability inventory: Shell command execution (mktemp) and filesystem write access. Sanitization: The skill does not escape, validate, or sanitize the conversation content before it is summarized and stored.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 10:44 AM
Security Audit — agent-trust-hub — handoff