solo-scope
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill uses
curlto download data from an external RSS feed (https://www.mixdao.world/feed). - COMMAND_EXECUTION (LOW): The agent is instructed to run a shell command (
curl) to fetch the data. - PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted content from an external RSS feed.
- Ingestion points: RSS feed items (fields:
title,description) fetched in Step 1 of the workflow. - Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore embedded instructions within the feed content.
- Capability inventory:
curlfor network requests and Markdown generation for output. - Sanitization: Absent; no logic is provided to validate or escape the content parsed from the XML.
Audit Metadata