Skills
skills/allinherog-star/ai-skills/ai-amazon-subscribe-save/Gen Agent Trust Hub

ai-amazon-subscribe-save

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources.\n
  • Ingestion points: Identified in references/form-schema.json and references/skill.json via parameters materialUrl, materialText, and materialFile.\n
  • Boundary markers: The skill instructions do not specify any delimiters or safety warnings to separate user-provided data from agent instructions.\n
  • Capability inventory: The scripts/run.py script performs network operations using the urllib.request library to transmit data to the AI Skills API at https://ai-skills.ai.\n
  • Sanitization: No evidence of input validation, escaping, or content filtering for the ingested materials was found in the provided code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:30 AM
Security Audit — agent-trust-hub — ai-amazon-subscribe-save