pp-scrape-creators
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from various social media platforms, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Comments, replies, transcripts, and posts from 28 social media platforms (Instagram, TikTok, YouTube, etc.).
- Boundary markers: Absent.
- Capability inventory: Execution of the
scrape-creators-pp-clibinary, local SQLite database access, and data transmission via external webhooks. - Sanitization: Not specified for the ingested content.
- [EXTERNAL_DOWNLOADS]: The skill fetches its primary binary and supporting libraries from the vendor's official repositories and package registries.
- Evidence: Installation via
npx -y @mvanhorn/printing-press-libraryandgo install github.com/mvanhorn/printing-press-library/.... - [DATA_EXFILTRATION]: The skill includes a
--deliver webhook:<url>functionality that allows the agent to send scraped data to non-whitelisted external domains. - [COMMAND_EXECUTION]: The skill acts as a wrapper for a command-line interface and requires the ability to execute shell commands for installation and runtime operations.
Audit Metadata