competitor-ad-tracking
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'scrapesocial' npm package, which is the core utility for its functionality.
- [COMMAND_EXECUTION]: The skill uses the 'scrapesocial' CLI to perform ad searches and data retrieval across platforms like Facebook, Google, and LinkedIn.
- [PROMPT_INJECTION]: The skill processes external ad data, creating a surface for indirect prompt injection. 1. Ingestion points: Data is ingested from third-party ad libraries via CLI commands in SKILL.md. 2. Boundary markers: The skill lacks explicit instructions to treat the extracted ad content as untrusted. 3. Capability inventory: The skill executes CLI commands and writes output to local files. 4. Sanitization: No evidence of input sanitization or validation is present in the skill's instructions.
Audit Metadata