social-media-writer

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill's use of local shell commands and script execution is consistent with its primary purpose of analyzing and generating social media content.
  • [PROMPT_INJECTION]: The skill processes reference examples to extract writing patterns, which is an architectural surface for indirect prompt injection. However, within the context of creative content generation, this risk is minimal and associated with the primary skill purpose.
  • Ingestion points: Reference files located in 'references/examples/social/'.
  • Boundary markers: No explicit delimiters are mentioned in the skill markdown to separate reference data from instructions.
  • Capability inventory: Uses local Bash and Python scripts for data processing and Write tools to save generated content.
  • Sanitization: No explicit sanitization or validation of input references is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 04:50 AM
Security Audit — agent-trust-hub — social-media-writer