creator-scraper-cv
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/export_to_csv.mjsscript performs local file system writes using thenode:fsmodule to save collected creator metrics to a CSV file. - [DATA_EXFILTRATION]: The skill transmits the
CV_API_KEYand user search parameters to the external vendor domainapi.creativault.vip. The default configuration uses unencrypted HTTP (port 80), which creates a risk of credential exposure during transmission. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its core function of scraping untrusted data from social media platforms.
- Ingestion points: Scraped profile data including usernames, nicknames, and bios are ingested through
scripts/search_creators.mjsandscripts/get_task_data.mjs. - Boundary markers: There are no boundary markers or explicit instructions provided to the agent to distinguish between its own logic and the potentially malicious instructions embedded in the external data.
- Capability inventory: The skill possesses capabilities for both network communication and local file system modification.
- Sanitization: The skill does not perform any validation or sanitization of the social media content before it is processed by the agent.
Audit Metadata