ux-audit
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local bash script (
sage/runtime/tools/sage-screenshot.sh) with a user-provided URL or localhost string as a parameter. This creates a potential command injection surface if the input is not strictly validated by the execution platform. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external websites.
- Ingestion points: External data is ingested via URLs and screenshots during the audit process (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters mentioned to prevent the agent from following instructions embedded in the analyzed web content.
- Capability inventory: The skill has the ability to execute shell commands and write files to the local
.sage/work/directory. - Sanitization: No sanitization or filtering of the external content or the URL parameter is specified in the skill logic.
Audit Metadata