cross-platform-audit
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and orchestration logic do not contain malicious patterns or security risks.
- [DATA_EXFILTRATION]: File operations are limited to audit results and shared scoring configurations within the skill directory. The skill does not access sensitive system paths or credentials, nor does it perform unauthorized network exfiltration.
- [REMOTE_CODE_EXECUTION]: The skill utilizes the platform's native task tools for parallel processing and does not execute remote scripts, untrusted binaries, or dynamic code strings.
- [PROMPT_INJECTION]: The skill processes external advertising data which creates an indirect prompt injection surface. This is considered safe as the data is used for analytical purposes within a controlled workflow. Ingestion points: User-supplied metrics, screenshots, and account exports defined in SKILL.md. Boundary markers: Absent. Capability inventory: Task spawning and local file read/write operations for generating reports. Sanitization: Absent.
Audit Metadata