social-media-content-repurposer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted source content provided by users for repurposing across social media platforms.
  • Ingestion points: The skill ingests data in the 'Analyze Source Content' step, where it extracts key messages and takeaways from user-provided blog posts, articles, or podcast transcripts.
  • Boundary markers: The instructions do not implement specific delimiters or 'ignore' directives to separate the source content from the agent's instructions, which could allow instructions embedded in a blog post to influence the agent.
  • Capability inventory: No capabilities for tool invocation, shell command execution, file system access, or network operations were found in the skill metadata or instructions.
  • Sanitization: The skill does not include any validation or sanitization steps to filter potential prompt injection patterns from the ingested source material.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:02 PM
Security Audit — agent-trust-hub — social-media-content-repurposer