msl
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security concerns were identified during the analysis of the skill's instructions and configuration files.
- [PROMPT_INJECTION]: The skill includes a detailed set of instructions ('MSL Kernel') and 'Fuses' to control agent output formatting. These instructions are functional guidelines for effective communication and do not attempt to bypass security filters or extract sensitive system information.
- [DATA_EXFILTRATION]: The instructions encourage a 'partitioning' phase where technical implementation details (tools, logs, abandoned attempts) are separated from the information delivered to the user. This serves as a control against the accidental disclosure of internal metadata or instrument details.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize context from the user's records. While this represents a data ingestion surface, the logic is focused on information filtering, and the skill itself does not provide the agent with executable capabilities that could be abused through malicious input.
Audit Metadata