add-provider-doc
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it accepts an untrusted
provider-nameargument that is interpolated into file paths and document content. - Ingestion points: The
[provider-name]argument and{PROVIDER}placeholders inSKILL.mdare used to generate file paths likedocs/usage/providers/{provider-name}.mdxand environment variables. - Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings for the user-supplied content.
- Capability inventory: The workflow involves writing to sensitive configuration files including
Dockerfile,Dockerfile.database, and.env.example. - Sanitization: There is no mention of validation or sanitization for the input provider name, which could lead to path traversal if the agent handles the string insecurely.
Audit Metadata