buzz-media-attachments

Warn

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONCREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute system tools including ffmpeg for video transcoding, ffprobe for metadata extraction, and a specialized buzz CLI for message delivery.
  • [CREDENTIALS_UNSAFE]: The workflow requires reading sensitive configuration data from ~/.hermes/.env. This file contains authentication tokens such as BUZZ_AUTH_TAG and BUZZ_PRIVATE_KEY.
  • [DATA_EXFILTRATION]: The skill accesses ~/.hermes/logs/gateway.log to extract channel identifiers from live message logs, which involves processing potentially sensitive chat history data.
  • [PROMPT_INJECTION]: The skill has an indirect injection surface by ingesting data from external log files. 1. Ingestion points: ~/.hermes/logs/gateway.log in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: subprocess.run, ffmpeg, buzz CLI in SKILL.md. 4. Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 3, 2026, 04:25 PM
Security Audit — agent-trust-hub — buzz-media-attachments