reboot-recovery
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or security vulnerabilities were identified in the skill instructions.
- [COMMAND_EXECUTION]: The skill utilizes a local utility script (
../../scripts/recovery_checkpoint.py) to perform deterministic state checks, which is a standard functional component for this use case. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from project documentation and state files. 1. Ingestion points:
../../references/REBOOT_RECOVERY.mdand durable project state files. 2. Boundary markers: None specified. 3. Capability inventory: Execution of../../scripts/recovery_checkpoint.pyand local file read/write operations. 4. Sanitization: None documented. This surface is considered low risk as it involves internal project resources.
Audit Metadata