context-bankruptcy
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and provides a methodology for auditing agent memory without using any executable code or tools.- [NO_CODE]: No scripts, binary files, or shell commands are included or referenced for execution. The functionality is entirely prompt-driven within the LLM context.- [DATA_EXPOSURE_AND_EXFILTRATION]: While the skill asks the user to provide memory exports or context as input for the audit process, it does not contain any instructions or tools to transmit this data to external servers or non-whitelisted domains.
Audit Metadata