handoff

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and acting upon session state data from external JSON files.
  • Ingestion points: The skill reads state information from JSON files (typically stored in .claude/handoffs/ or user-defined paths), including pending_steps, constraints, and decisions.
  • Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded in the loaded state files.
  • Capability inventory: The skill uses the Read and Write tools to interact with the project filesystem, providing a mechanism for actions directed by the loaded state.
  • Sanitization: No validation or sanitization is performed on the JSON content before the agent adopts the tasks and constraints defined within it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 08:01 PM
Security Audit — agent-trust-hub — handoff