Sleep
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to perform file system operations to migrate user data from legacy directories to a new consolidated path. Specifically, it requests moving data from
~/sleep/or~/clawic/sleep/to~/Clawic/data/sleep/if found. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from several local files created or updated based on user input, which serves as a potential attack surface for indirect prompt injection.
- Ingestion points: The agent reads from
~/Clawic/data/sleep/diary.md,~/Clawic/data/sleep/config.yaml, and~/Clawic/data/sleep/memory.mdto derive coaching protocols and status updates. - Boundary markers: No explicit boundary markers or 'ignore' instructions are used when reading these files.
- Capability inventory: The skill possesses file read, write, and move (migration) capabilities within the user's home directory. It does not possess arbitrary code execution or outbound network capabilities (other than providing documentation links).
- Sanitization: No explicit sanitization or validation of the content of these files is described in the instructions.
Audit Metadata