kryptogo-pay-checkout
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the
$ARGUMENTSvariable inSKILL.mdto customize the integration process. - Ingestion points: User input provided in Step 1 of
SKILL.mdto select integration method and framework. - Boundary markers: Absent; there are no delimiters or specific instructions for the agent to ignore instructions embedded within the user arguments.
- Capability inventory: The skill uses
Write,Edit, andBashtools to modify the project environment. - Sanitization: Absent; the skill does not specify validation or filtering for the user-supplied arguments before they are used to drive agent actions.
- [SAFE]: All external API calls and package installations target official KryptoGO domains (wallet.kryptogo.app, studio.kryptogo.com) and vendor-owned libraries (@kryptogo/payment), which are consistent with the skill's stated purpose.
- [SAFE]: The skill promotes secure development practices by instructing users to manage credentials via environment variables and ensure sensitivity files like .env are excluded from version control.
Audit Metadata