skills/reddb-io/red-skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute the mktemp command to generate a temporary file path. This represents a shell command execution that interacts with the host filesystem.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests and processes untrusted conversation history to generate a handoff document without implementing security boundaries.
  • Ingestion points: The entire conversation history is analyzed to create the summary.
  • Boundary markers: No delimiters or instructions are used to separate the system instructions from the potentially malicious content within the conversation.
  • Capability inventory: The skill utilizes shell command execution via mktemp and writes the resulting summary to the disk.
  • Sanitization: No sanitization, validation, or escaping is performed on the conversation data before it is written to the output file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:33 PM
Security Audit — agent-trust-hub — handoff