write-blog-post

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing untrusted external data.
  • Ingestion points: The skill instructions in SKILL.md explicitly direct the agent to "turn notes, a transcript or a social post into a blog post" and to use "facts the user gives you or that are in their source."
  • Boundary markers: There are no instructions to use delimiters or specific boundary markers to separate untrusted source content from the agent's instructions, nor are there warnings to ignore embedded commands.
  • Capability inventory: The skill possesses significant capabilities, including the ability to upload media from arbitrary URLs (upload_media_from_url), create and modify web content (create_post, update_post), and publish content live to the internet (schedule_post).
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the data retrieved from external transcripts or social posts before it is processed or published.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 07:17 PM