Japan
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions in
setup.mdto executemkdir -p ~/japanfor initializing the local storage directory. While there is a minor path inconsistency between the setup script and the frontmatter config, the command itself is a standard, benign initialization step.- [INDIRECT_PROMPT_INJECTION]: The skill uses a local file to maintain trip context and user preferences, creating a surface for indirect prompt injection. - Ingestion points: The agent reads user preferences from
~/Clawic/data/japan/memory.mdas described inSKILL.mdandsetup.md. - Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are present in the skill files.
- Capability inventory: The skill's scripts (
setup.md) demonstrate the ability to execute shell commands (mkdir) and perform local file operations within the defined data path. - Sanitization: There is no evidence of sanitization or validation of the content retrieved from the memory file.
Audit Metadata