s3-management
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines legitimate AWS S3 management tools. No hardcoded credentials, obfuscation, or malicious patterns were found.
- [NO_CODE]: This skill consists of metadata and documentation; it contains no executable code or scripts.
- [PROMPT_INJECTION]: The skill includes tools to read external object data, creating a surface for indirect prompt injection. Evidence: (1) Ingestion points: Content retrieved from S3 via get_object in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: S3 write and delete tools (put_object, delete_object, presigned_url) in SKILL.md. (4) Sanitization: Absent.
Audit Metadata