skills/cursor/plugins/add-dictation/Gen Agent Trust Hub

add-dictation

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted audio data, which is converted to text and then inserted into the application's input field.
  • Ingestion points: Transcribed text is received from the Grok API endpoints https://api.x.ai/v1/stt and wss://api.x.ai/v1/stt as documented in SKILL.md.
  • Boundary markers: The provided implementation examples do not use delimiters or instructions to treat the resulting transcript as untrusted data.
  • Capability inventory: The insertAtCursor(text) function (mentioned in SKILL.md) places the potentially malicious transcription into the user's active composer.
  • Sanitization: There is no evidence of sanitization or filtering of the transcribed text before it is inserted into the UI context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 09:12 AM
Security Audit — agent-trust-hub — add-dictation