write-docs

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for writing SDK documentation, including tone, confidence, and specific MDX formatting rules.\n- [SAFE]: Links to the tldraw repository on GitHub are for reference purposes and point to a well-known open-source project.\n- [PROMPT_INJECTION]: The skill facilitates the creation and modification of files in apps/docs/content/ based on user input, creating a surface for indirect prompt injection.\n
  • Ingestion points: User requests to generate or update documentation content.\n
  • Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore instructions embedded within the user-provided documentation text.\n
  • Capability inventory: The skill instructs the agent to write files to the documentation content directory.\n
  • Sanitization: No validation or sanitization of the documentation content is performed before writing to disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 04:52 PM
Security Audit — agent-trust-hub — write-docs