dead-air-cleanup
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for editing audio and video content. It utilizes platform-specific tools for silence detection and timeline editing without any evidence of malicious intent, unauthorized command execution, or data exfiltration.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes transcript data to perform word-timed cuts, which represents an attack surface for indirect prompt injection if the source media contains adversarial text. However, this is inherent to its primary purpose as an editing tool.\n
- Ingestion points: Transcripts used for
cutRangeslogic (SKILL.md).\n - Boundary markers: Not explicitly defined in the instructions.\n
- Capability inventory:
trimSilence,cutRanges, andagentWorkspacefor timeline modification and review (SKILL.md).\n - Sanitization: Not specified within the skill instructions.
Audit Metadata