handoff

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history to create a summary. If the conversation contains malicious instructions, they could be included in the output document.
  • Ingestion points: Current conversation context (SKILL.md).
  • Boundary markers: Absent; the skill does not specify delimiters for the generated content.
  • Capability inventory: File writing to the system's temporary directory.
  • Sanitization: The skill explicitly instructs the agent to redact sensitive information such as API keys and passwords.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill directs the agent to save summaries to the user's OS temporary directory rather than the current workspace. This moves conversation data into a temporary file system location.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 09:17 AM
Security Audit — agent-trust-hub — handoff