repurpose-content

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, creating a surface for indirect prompt injection where an attacker could embed hidden instructions in a blog post or transcript.
  • Ingestion points: The skill reads user-provided text, articles from links, video transcripts, and podcast notes (SKILL.md, Step 1).
  • Boundary markers: The instructions do not specify the use of delimiters or clear warnings to the agent to ignore instructions embedded within the source content.
  • Capability inventory: The skill has the ability to write data to external platforms using create_post, bulk_create_posts, and schedule_post (SKILL.md, Step 8).
  • Sanitization: No explicit sanitization or filtering of external content is described before the content is used to generate social media posts.
  • Mitigation: The risk is mitigated by Step 7 and 8, which require the agent to present drafts to the user for confirmation before any tool is invoked to create or schedule posts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 06:54 AM