skills/yuias/skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git rev-parse and git status to document the project's state during the save phase.
  • [DYNAMIC_EXECUTION]: During restoration, the skill extracts and executes shell commands from the 'Verification' section of the .claude/handoff.md file.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingest project state from a local file, which could be exploited if an attacker modifies the handoff note to include malicious commands.
  • Ingestion points: The .claude/handoff.md file is read during the restore operation.
  • Boundary markers: No explicit markers are used to isolate untrusted content from the rest of the prompt.
  • Capability inventory: The skill can execute shell commands and modify project files.
  • Sanitization: The agent is instructed to wait for user confirmation before editing any files, providing a manual security check.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 02:27 PM