handoff-resume
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local handoff files, which presents a surface for indirect prompt injection.
- Ingestion points: Reads content and frontmatter from markdown files within the
docs/handoffs/directory. - Boundary markers: The instructions do not define delimiters or markers to isolate the handoff data from the agent's system instructions.
- Capability inventory: The skill is permitted to read and write files, move documents, and execute
git status. - Sanitization: No content validation or sanitization is performed before the agent follows the 'Next Steps' extracted from the handoff documents.
Audit Metadata