bolna-voice-prompt

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is primarily instructional and does not contain executable code, remote dependencies, or hidden commands. All patterns observed are consistent with the stated purpose of voice-agent prompt engineering.
  • [PROMPT_INJECTION]: The skill features a 'Transcript Diagnosis and Fix Workflow' that ingests untrusted data in the form of call transcripts provided by the user. This creates a surface for indirect prompt injection where instructions hidden in the transcript could attempt to influence the agent's behavior.
  • Ingestion points: User-provided call transcripts processed in references/transcript-workflow.md.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions for transcript data are defined.
  • Capability inventory: The skill generates and modifies prompt text; it has no file-system or network capabilities.
  • Sanitization: No sanitization of the input transcript content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 08:33 AM
Security Audit — agent-trust-hub — bolna-voice-prompt