scrapeatlas-setup

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses official vendor resources, including the @scrapeatlas/cli package and scrapeatlas.com domains for authentication and data retrieval.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from web sources which could contain malicious instructions.
  • Ingestion points: Command output from scrapeatlas CLI tools (e.g., bluesky profile, tiktok profile) as described in SKILL.md.
  • Boundary markers: None provided in the command examples to delimit tool output from the agent's context.
  • Capability inventory: Shell command execution for CLI operations and local configuration file writes (~/.config/scrapeatlas/config.json).
  • Sanitization: No specific sanitization or filtering of the retrieved data is documented in the setup instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 07:21 PM