social-media-posts

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A comprehensive review of the skill's instructions, metadata, and workflows revealed no malicious patterns, such as obfuscation, credential exfiltration, or unauthorized command execution.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) because it is designed to read and repurpose external content from user-provided file paths or URLs. This is a core functional requirement and is considered low risk given the skill's limited capabilities.
  • Ingestion points: The workflow specifies reading 'Topic or source content' from user-provided paths or URLs in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to isolate or ignore potentially malicious commands embedded within the ingested source material.
  • Capability inventory: The skill is granted access to standard file system tools including Read, Write, Glob, and Grep, which are used to process content and save results to a local directory (.jez/artifacts/).
  • Sanitization: The instructions do not define any sanitization or validation routines for the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 11:54 PM