peach-handoff

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface. The skill reads and summarizes content from session handoff files (docs/handoff/**/*.md), which is an ingestion point for untrusted or previously recorded data that could contain malicious instructions.\n
  • Ingestion points: The Load mode reads markdown files from the docs/handoff/ directory.\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the loaded file content as untrusted data or to ignore embedded instructions.\n
  • Capability inventory: The skill has access to the Bash, Write, and Read tools, which could be leveraged if the agent inadvertently follows instructions embedded in a handoff file.\n
  • Sanitization: The skill does not perform any sanitization, filtering, or validation of the content within the handoff files before processing them for summary and task suggestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 03:56 AM