facebook-ads
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from npm. This is a vendor-owned resource used for authentication and API interaction.
- [COMMAND_EXECUTION]: Executes membrane CLI commands to manage authentication, list connections, and perform ad management tasks.
- [PROMPT_INJECTION]: Potential for indirect prompt injection as the skill retrieves external data from the Facebook Ads API. 1. Ingestion points: Results from membrane action run and membrane request (SKILL.md). 2. Boundary markers: No explicit markers or warnings are present for API outputs. 3. Capability inventory: Network requests and command execution via Membrane CLI (SKILL.md). 4. Sanitization: No evidence of output sanitization or validation of data retrieved from the API.
Audit Metadata