c-broll
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes data from scripts and SRT files.
- Ingestion points: Script scenes and SRT transcripts (SKILL.md).
- Boundary markers: None identified. There are no explicit instructions to the agent to treat external text as data only.
- Capability inventory: The skill has access to Bash and file system tools (Read, Write, Edit) to manage and archive media assets.
- Sanitization: No sanitization or validation routines for external content are specified.
- [COMMAND_EXECUTION]: The skill performs shell-based file operations to manage media assets.
- Evidence: The 'Archiving from Production' section uses the Bash tool to execute 'cp' commands for moving media files between production and library directories.
Audit Metadata