general-edit
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions without any associated scripts, executables, or network operations. No malicious patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves reading potentially untrusted data such as transcripts and briefs. While this presents an ingestion surface, the risk is limited as the skill's capabilities are restricted to media manipulation.
- Ingestion points: Instructions in
SKILL.mddirect the agent to read transcripts, scene understanding data, and project briefs. - Boundary markers: No specific boundary markers or delimiters are used to separate untrusted data from instructions.
- Capability inventory: The skill references vendor-specific tools for media inspection (
source_inspect,audio_inspect) and timeline editing (addClip,replaceClipMedia). - Sanitization: No sanitization or validation steps for external content are described.
Audit Metadata