status
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
ai-memory --versionandai-memory doctorto diagnose the installation. These commands are local to the environment and are used to provide status reports to the user. - [INDIRECT_PROMPT_INJECTION]: The skill processes output from the
ai-memory doctorcommand to provide a summary to the user. - Ingestion points: Output from the
ai-memory doctorcommand is read into the agent's context. - Boundary markers: Absent; the instructions do not specify delimiters for the tool output.
- Capability inventory: The skill utilizes shell command execution for the
ai-memorybinary. - Sanitization: Absent; the agent is instructed to summarize the output as provided by the tool.
Audit Metadata