web-scraping-olostep

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The Setup section in SKILL.md contains shell instructions that use python3 to read local files and set environment variables.
  • [DATA_EXFILTRATION]: The skill is configured to read from ~/.gooseworks/credentials.json. This data is used as a Bearer token in requests to api.gooseworks.ai, which is the official vendor API.
  • [PROMPT_INJECTION]: The skill's core functionality involves scraping and analyzing external web content, which exposes the agent to indirect prompt injection.
  • Ingestion points: Data retrieved from external URLs via the Create Scrape, Start Crawl, and Create Answer endpoints.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are provided for processed content.
  • Capability inventory: Network requests via curl and AI-driven data extraction and analysis.
  • Sanitization: No explicit sanitization or validation of the fetched web content is described in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:14 PM
Security Audit — agent-trust-hub — web-scraping-olostep