social-media-strategy
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional markdown files, reference documents, and a simple Python validation script. Analysis of all files shows no evidence of malicious patterns.
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/check-output.py. This script performs basic text validation (length check and keyword presence) on a local file path. It does not perform network operations, access sensitive system files, or execute arbitrary shell commands. - [PROMPT_INJECTION]: The instructions follow standard formatting for AI agent skills and do not contain any bypass attempts, role-play injections, or instructions to ignore safety guidelines.
- [DATA_EXFILTRATION]: There are no network-capable commands (curl, wget) or attempts to access sensitive environment variables or credential files (e.g., .env, .ssh).
- [EXTERNAL_DOWNLOADS]: The skill does not download external packages or execute remote code. It relies solely on local files provided within the skill package.
Audit Metadata