security-scan
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a 'YOLO mode' which explicitly instructs the agent to 'carry out actions without asking again after the initial mode choice'. This instruction encourages the agent to bypass human-in-the-loop confirmation for system modifications, increasing the impact of potential exploitation.- [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) due to the following factors:
- Ingestion points: The agent is tasked with reading external, potentially attacker-controlled data such as 'suspicious processes', 'autoruns', and 'unwanted software' (SKILL.md).
- Boundary markers: There are no defined delimiters or instructions to ignore potential commands embedded within the system data being scanned.
- Capability inventory: In 'YOLO mode', the agent is granted the capability to modify system state based on its findings without iterative approval.
- Sanitization: The instructions do not include any steps for the agent to sanitize or validate the content of the processes or files it inspects before acting upon them.
Audit Metadata