x-article-converter

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as credential theft, remote code execution, or persistence mechanisms were detected in the skill definition.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override agent behavior.
  • [DATA_EXFILTRATION]: The skill does not access sensitive system files or credentials. Network activity is limited to standard web searches for public handle information.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source articles which presents a surface for indirect instructions. 1. Ingestion points: Reading source articles in Step 1. 2. Boundary markers: Absent. 3. Capability inventory: Writing content to markdown files. 4. Sanitization: Absent. The risk is assessed as low given the restricted nature of the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:38 AM