repurpose-content

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 processing untrusted data to perform actions with side effects.
  • Ingestion points: The skill ingests arbitrary long-form content provided by the user or fetched from external URLs via the agent's web access (SKILL.md, Step 1).
  • Boundary markers: There are no instructions to use delimiters or "ignore embedded instructions" warnings when the agent processes the retrieved content.
  • Capability inventory: The skill has access to sensitive capabilities including listing accounts (list_accounts), fetching platform-specific rules (get_platform_rules), uploading media (upload_media_from_url), and creating or scheduling social media posts (create_post, bulk_create_posts, schedule_post).
  • Sanitization: There is no mention of sanitizing, escaping, or validating the source content before it is used to draft social media posts or interact with the platform tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 07:17 PM