company-intel

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. Ingestion points: Scraped website data enters the agent context via the scrapegraph API proxy call in SKILL.md. Boundary markers: Absent; there are no delimiters or warnings to ignore instructions within the scraped content. Capability inventory: Network operations using curl and shell command execution using python3 are present in SKILL.md. Sanitization: No escaping or filtering of the external data is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to api.gooseworks.ai (vendor API) and references npx for authentication. These are standard operations within the author's tooling environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:06 PM