skills/dmmulroy/.dotfiles/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill explicitly instructs the agent to redact sensitive information, including API keys, passwords, and personally identifiable information (PII), which is a key security best practice for handling conversation data.\n- [SAFE]: Saving output to the operating system's temporary directory is a standard and acceptable practice for transient data that does not belong in the primary workspace.\n- [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any executable scripts, binary files, or external dependencies, significantly limiting its security risk profile.\n- [SAFE]: While the skill summarizes conversation history—creating a surface for indirect prompt injection—the risk is managed through explicit redaction instructions and the administrative nature of the task.\n
  • Ingestion points: User conversation history and workspace artifacts (PRDs, plans, ADRs, etc.) mentioned in SKILL.md.\n
  • Boundary markers: No specific delimiters or safety warnings for the generated summary output are defined.\n
  • Capability inventory: File system write access used to save the summary to the OS temporary directory.\n
  • Sanitization: Instructions are provided to redact all credentials and PII from the final document.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:56 AM
Security Audit — agent-trust-hub — handoff