enrich-api-page
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches technical details from the official Telegram Bot API documentation (
core.telegram.org) and package documentation from JSR (jsr.io). These are well-known and authoritative sources for the technical content being generated. - [COMMAND_EXECUTION]: Uses the
Bashtool to performGrepsearches against local TypeScript definition files innode_modules/@gramio/contexts/. This is used to verify method signatures and ensure that generated code examples are accurate and type-safe. - [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by reading data from external web pages.
- Ingestion points: External data is retrieved via
WebFetchfromcore.telegram.org. - Boundary markers: The instructions provide clear boundaries by specifying which frontmatter fields and markdown sections to edit, and explicitly forbid modification of generated blocks between
<!-- GENERATED:START -->and<!-- GENERATED:END -->tags. - Capability inventory: The skill has permissions to write and edit documentation files and execute
Bashfor pattern searching. - Sanitization: No specific sanitization of external documentation text is described, though the output is directed into static documentation files rather than executable scripts.
Audit Metadata