handoff-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as user notes, task lists, and messages to generate structured handoff documentation. * Ingestion points: The 'What to ask for' section defines user-provided notes, task lists, and brain dumps as primary inputs in the file SKILL.md. * Boundary markers: No specific delimiters or boundary markers are defined for the input data within the prompts. * Capability inventory: The skill includes the capability to save text to external notes applications via a connector tool as described in SKILL.md. * Sanitization: The instructions in SKILL.md explicitly direct the agent to identify and exclude credentials such as passwords and door codes from the output, advising the user to communicate them via secure channels instead.
- [SAFE]: No malicious command execution, data exfiltration, or obfuscation patterns were detected. The skill promotes secure handling of sensitive data by instructing the AI to avoid hardcoding secrets in the resulting notes.
Audit Metadata