blog-promotion

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of untrusted external content.
  • Ingestion points: SKILL.md (Process Step 1: 'Read the full blog post at the URL provided by the user').
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded commands within the fetched content.
  • Capability inventory: The agent uses tools to fetch and analyze content from remote URLs.
  • Sanitization: Absent. Content retrieved from external URLs is not filtered or validated before being used to generate social media posts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:40 AM