x-twitter-growth
Fail
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: HIGHDATA_EXFILTRATION
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: Detected a directory traversal attempt in SKILL.md using the string
../../../marketing-skill/x-twitter-growth/SKILL.md. This pattern is used to navigate above the current directory and access files in parent or sibling directories. In an AI agent environment, this indicates an attempt to escape the skill sandbox and read files from the host system or other project folders, which could lead to sensitive data exposure.
Recommendations
- AI detected serious security threats
Audit Metadata