Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from Instagram, such as user comments and analytics, which creates a surface for indirect prompt injection.
- Ingestion points: Instagram comments, insights, and follower data (SKILL.md).
- Boundary markers: No boundary markers or instructions to ignore embedded commands are specified.
- Capability inventory: The skill utilizes curl and jq for network operations as defined in the metadata.
- Sanitization: No sanitization or input validation logic is present in the manifest.
- [EXTERNAL_DOWNLOADS]: The skill metadata defines dependencies on the external binaries curl and jq, which are standard utilities for API interaction.
Audit Metadata