save-web-page
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Command Execution (LOW): The skill instructs the agent to run the 'monolith' command using variables for filenames and URLs. If these inputs are not properly sanitized by the agent, it could lead to command injection or unauthorized file access.
- Indirect Prompt Injection (LOW): The skill retrieves data from external URLs that are not controlled by the user. This data could contain malicious instructions intended to manipulate the agent's future actions. 1. Ingestion points: External URLs provided to the monolith command in SKILL.md. 2. Boundary markers: Not specified in the skill instructions. 3. Capability inventory: Execution of the monolith binary. 4. Sanitization: None specified for the input data.
Audit Metadata