content-create
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGH
Full Analysis
- SAFE (LOW): No executable code, scripts, or configuration files capable of performing actions were detected. The skill consists entirely of markdown documentation.\n- PROMPT_INJECTION (INFO): While the skill ingests user input for content topics and brand voice, it lacks system-level capabilities such as command execution or network access, making the indirect prompt injection surface a negligible risk (Tier: INFO).\n- AUTOMATED SCANS (LOW): The phishing alerts for 'instagram.md' and 'linkedin.md' were evaluated and determined to be false positives. They are likely triggered by standard marketing templates such as 'Link in bio' or 'DM me for details', which simulate social engineering patterns but do not contain actual malicious URLs in the skill files.
Recommendations
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata