handoff-list
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill only performs read operations on files within a specific local directory (
.handoffs/). It does not use any tools that would allow for network communication or system modification. - [PROMPT_INJECTION]: While the skill processes untrusted data from local handoff files, which is a surface for indirect prompt injection, the impact is low as the agent only summarizes and translates the content for display.
- Ingestion points: Contents of
.handoffs/handoff-NNNN.md(SKILL.md) - Boundary markers: Use of frontmatter and
<handoff-summary>tags (SKILL.md) - Capability inventory: File reading and text summarization; no dangerous tools requested
- Sanitization: Explicit instructions to flag malformed files (SKILL.md)
Audit Metadata