manufacturing-monthly-selfcheck-free

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md documentation includes a pre-written prompt for users to give to their AI assistant. This text uses high-pressure language such as 'I have authorized installing dependencies' and 'do not confirm for me' to influence the agent's behavior during a purchase flow.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted manufacturing data tables provided by the user, creating a surface for potential instruction injection if the data contains malicious text.
  • Ingestion points: The text property of the input payload in scripts/engine/parts/ files.
  • Boundary markers: None present in the parsing logic.
  • Capability inventory: The skill is configured with Bash and Read tool access.
  • Sanitization: No sanitization is performed on the input text before processing.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to execute a script using npx targeting the @alipay/agent-payment package, which is a well-known service.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — manufacturing-monthly-selfcheck-free