social-content

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured templates and strategies for social media content creation, including hooks, content pillars, and platform-specific formatting guidelines.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies .claude/product-marketing-context.md as a source of context. While this ingestion of external data is a potential vector for indirect prompt injection, the risk is negligible as the skill lacks high-risk system capabilities.
  • Ingestion points: .claude/product-marketing-context.md (SKILL.md).
  • Boundary markers: The skill does not implement explicit delimiters for external context data.
  • Capability inventory: None detected; the skill is focused on text generation and does not access network resources or execute shell commands.
  • Sanitization: No sanitization is performed on the imported context data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — social-content