social-post-generator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a standard prompt engineering template designed for content generation. It defines specific workflows and formatting rules for social media platforms without requesting unnecessary permissions or performing risky operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied content, such as article links and text descriptions, to generate social posts. This ingestion creates a potential surface for indirect prompt injection if the source material contains malicious instructions. However, this is a standard risk for all LLM-based content transformation tools and is mitigated by the agent's core safety guardrails.
- Ingestion points: Step 1 (Collect Inputs) collects 'Content Material' (links, article paragraphs, ideas) from the user.
- Boundary markers: The skill does not explicitly define boundary markers or 'ignore' instructions for the ingested material.
- Capability inventory: The skill uses file-writing capabilities to save the output as a markdown file.
- Sanitization: No explicit sanitization of user-provided content is defined in the instruction set.
Audit Metadata