session-migrate
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the current conversation history to generate a prompt for a future agent session, creating a potential surface for instructions to persist across sessions.
- Ingestion points: Current session context, including user messages and previous tool outputs, are processed according to the workflow in
SKILL.md. - Boundary markers: The skill uses a structured Markdown template, but it does not include explicit instructions for the receiving agent to treat summarized content as potentially untrusted or to ignore embedded instructions within that data.
- Capability inventory: While the skill itself contains no executable code, the generated output is designed to guide a future agent which typically possesses full file system and tool access.
- Sanitization: No sanitization, escaping, or filtering of the ingested session data is specified before it is interpolated into the handoff template.
- [SAFE]: The skill includes a specific rule for the agent to avoid including secrets, tokens, credentials, or private data in the handoff prompt unless explicitly requested and safe, which aligns with security best practices.
Audit Metadata