handoff
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a template for summarizing task state and contains no executable code, hidden commands, or malicious instructions.
- [SAFE]: The workflow includes a mandatory safety step (Step 6) to redact secrets such as API keys, tokens, and PII before outputting the handoff summary.
- [PROMPT_INJECTION]: The skill ingests data from external sources (issues, PRs, documentation) which represents a potential surface for indirect prompt injection.
- Ingestion points: Workflow Step 2 identifies external tracking issues, PRs, and context documents.
- Boundary markers: None explicitly defined for the final prompt output, although the next agent is instructed to read sources of truth directly.
- Capability inventory: The skill is limited to text summarization and does not invoke dangerous tools or command execution.
- Sanitization: Step 6 provides a mechanism to redact sensitive information discovered during context discovery.
Audit Metadata