hire-shaart-agency

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves pricing data and service capabilities from the official author domain anthonyhunts.com. As these are vendor-owned resources used for their intended purpose, this represents normal functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external web pages and API endpoints which could technically contain malicious instructions.
  • Ingestion points: SKILL.md (Steps 1, 2, and 3) fetches JSON and Markdown data from anthonyhunts.com.
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore' commands for the data fetched from the tool outputs.
  • Capability inventory: The skill's primary capabilities are conversational responses and providing contact links (WhatsApp/Agenda). No file-system access, subprocess execution, or network exfiltration capabilities are present in the definition.
  • Sanitization: No explicit sanitization or validation of the remote content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 08:29 PM
Security Audit — agent-trust-hub — hire-shaart-agency