social-media-scraping-scrapecreators
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill is designed to read from
~/.gooseworks/credentials.jsonto retrieve API keys. While this is a sensitive path, it is a vendor-owned configuration file used for its intended purpose of authenticating with the author's own API. - [COMMAND_EXECUTION]: The skill uses
python3 -cto parse local JSON configuration files andcurlto interact with the vendor's API endpoints atapi.gooseworks.ai. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple social media platforms, including X/Twitter, LinkedIn, Instagram, and TikTok, which represents a potential surface for indirect prompt injection attacks.
- Ingestion points: Data retrieved from various scraping endpoints (e.g.,
/v1/twitter/profile,/v1/linkedin/post) as documented inSKILL.md. - Boundary markers: The instructions do not specify any delimiters or safety warnings to the agent regarding the processing of scraped content.
- Capability inventory: The skill has the capability to perform network requests and read local configuration files.
- Sanitization: There are no evident mechanisms to sanitize or filter out potential malicious instructions embedded in the scraped social media content.
Audit Metadata