handoff

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the handoff documentation file.
  • Ingestion points: The 'Resume Mode' phase reads the 'docs/HANDOFF.md' file and automatically processes the '## Artifacts' section.
  • Boundary markers: The instructions do not define boundary markers or 'ignore' instructions when reading the contents of files listed in the artifacts section.
  • Capability inventory: The skill has the capability to read any local text file and run 'git' commands for status and history.
  • Sanitization: There is no validation or sanitization of the file paths provided in the '## Artifacts' section, meaning a malicious file could point the agent to sensitive locations like '.env' or SSH configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:28 PM