tinacms
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill demonstrates safe security practices by explicitly instructing the user to store sensitive tokens like
TINA_TOKENin environment variables rather than hardcoding them. It also correctly warns that the generated client embeds the token and should be limited to server-side code. - [EXTERNAL_DOWNLOADS]: The skill uses official package runners (
npx @tinacms/cli) to initialize the project, which is standard practice for this library. - [INDIRECT_PROMPT_INJECTION]: The skill processes external content files. 1. Ingestion points: Markdown and MDX files in the
content/directory. 2. Boundary markers: None explicitly mentioned. 3. Capability inventory: Local file modification and GraphQL querying. 4. Sanitization: Rendering is handled by the officialTinaMarkdowncomponent.
Audit Metadata