social-media-content-repurposer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No malicious instructions, jailbreak attempts, or system prompt extraction patterns were detected. The instructions are focused on content formatting and tone adjustment.
- [Data Exposure & Exfiltration] (SAFE): There are no network operations (curl, fetch, etc.) or hardcoded credentials. The skill does not access sensitive local file paths.
- [Remote Code Execution] (SAFE): The skill consists of a single markdown file with no executable scripts, remote downloads, or package dependencies.
- [Indirect Prompt Injection] (SAFE): While the skill is designed to ingest and process untrusted user data (blog posts, articles), it lacks any functional capabilities (shell access, file writing, or network transmission) that could be exploited. Per the adversarial reasoning framework, the risk is negligible as the primary purpose is text transformation.
- Ingestion points: User-provided source content (blog posts, videos, articles).
- Boundary markers: Not explicitly defined in the prompt structure.
- Capability inventory: No code execution or external tool usage available.
- Sanitization: None required as the output is restricted to text generation within the AI's chat context.
Audit Metadata