handoff-prompt-writer
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or associated templates.
- [DATA_EXPOSURE]: The skill exhibits proactive security awareness by explicitly instructing the agent to remove secrets, tokens, credentials, and personal data from the final handoff file. It specifically warns against harvesting secrets from environment files, logs, or tool results.
- [EXTERNAL_DOWNLOADS]: The skill references technical documentation from well-known and trusted organizations (Anthropic, OpenAI, Microsoft, and LangChain) for context engineering guidelines. These are informational references and do not involve the download of executable code or scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates untrusted repository data (diffs, logs, and command results) into a prompt for a successor agent. While this creates a potential surface for indirect injection, the skill mitigates risk by requiring the successor to verify outcomes and prioritizing explicit user intent over inferred data from the file system.
Audit Metadata