p-handoff

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes session history and project files to generate a handoff document, which represents a potential surface for indirect injection from untrusted file content.
  • Ingestion points: Reads current workspace files, Git status, and command history.
  • Boundary markers: None explicitly defined in the output template instructions.
  • Capability inventory: Involves file system read operations and writing the summary to a user-specified or temporary path.
  • Sanitization: The skill contains explicit instructions to mask keys, tokens, personal information, and sensitive file paths before writing the handoff document.
  • [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration without any executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 07:50 AM