social-media-posts

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is entirely focused on content creation and formatting. It does not request unsafe permissions, access sensitive files, or perform network operations.
  • [PROMPT_INJECTION]: The skill includes instructions to ingest and analyze user-provided reference posts or search past posts to match an author's writing style. This creates a surface for indirect prompt injection where untrusted content could attempt to influence the agent's behavior.
  • Ingestion points: SKILL.md ('Ask the user for 3-5 reference posts', 'search past posts if available').
  • Boundary markers: None provided in the instruction set to delimit user content from instructions.
  • Capability inventory: The skill utilizes an image_generate tool to create visuals for posts.
  • Sanitization: There are no instructions to sanitize or validate the content of the reference posts before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:11 AM
Security Audit — agent-trust-hub — social-media-posts