x-article-converter

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source articles to extract names and insights for social media conversion.\n
  • Ingestion points: The skill reads source articles as input as described in Step 1 of SKILL.md.\n
  • Boundary markers: There are no specific delimiters or instructions to ignore embedded instructions within the article text provided to the agent.\n
  • Capability inventory: The skill uses the WebSearch tool and performs file system write operations to generate markdown assets.\n
  • Sanitization: No validation or sanitization is performed on the input content before it is interpolated into search queries or output files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 12:32 PM