payments-stripe
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFEPROMPT_INJECTIONCREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted data from project repositories.
- Ingestion points: Accesses and operates on the local project directory or git repository (SKILL.md).
- Boundary markers: Absent. The skill does not define delimiters or provide instructions to ignore potentially malicious content within the files it processes.
- Capability inventory: The skill can perform local repository edits, update environment variables via API, and trigger deployments (SKILL.md).
- Sanitization: Absent. There is no evidence of validation or sanitization of the content read from external repositories.
- [CREDENTIALS_UNSAFE]: The skill references the use of sensitive local credential files.
- Evidence: Instructions specify that authentication must come from
~/.build-host/credentials.json. While this is the expected location for the vendor's tool credentials, it represents access to sensitive data on the host system. - [COMMAND_EXECUTION]: The skill performs automated file system and API operations.
- Evidence: The skill is designed to perform local repository edits and interact with the build.host API endpoints for environment management and deployments (
/api/projects/:uuid/envs,/api/projects/:uuid/deploy).
Audit Metadata