coze-asr

Warn

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/asr.mjs utilizes the jiti library to dynamically import and execute code from a path (../../../src/skill-cli.ts) that resides outside of the skill's directory. This pattern of executing code via relative path traversal depends on the specific directory structure of the host environment.
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch audio data from remote URLs provided via the --url or -u command-line arguments.
  • [DATA_EXFILTRATION]: The skill reads local files specified through the --file or -f arguments and uploads their contents to the Coze ASR API. While this is the intended functionality, it establishes a data path from the local file system to an external service.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing external data from audio files or URLs. The resulting transcription is returned to the agent without explicit sanitization or boundary markers.
  • Ingestion points: --url and --file arguments in SKILL.md.
  • Boundary markers: Absent. There are no instructions for the agent to treat the transcribed output as untrusted content.
  • Capability inventory: The skill script has the ability to read local files and initiate network connections.
  • Sanitization: Absent. The raw text recognized from the audio is printed directly to standard output.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 05:47 AM
Security Audit — agent-trust-hub — coze-asr