video-script
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a specific bash command string (
grep,sed, andwc) in the 'Timing Validation' section of SKILL.md. It instructs the agent to execute this command to extract narrator dialogue and calculate word counts from a locally generated file. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data to generate video scripts, which exposes an indirect prompt injection surface.
- Ingestion points: User-provided inputs such as 'Topic', 'Key points', 'CTA', 'Tone', and 'Audience' are gathered in Phase 1 and used throughout the script generation process.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when interpolating user data into the generated script.
- Capability inventory: The skill has the capability to write the final output to a file (
video-script.md) and execute local shell commands for validation. - Sanitization: No sanitization or validation of user-provided strings is mentioned before they are processed or written to the file system.
Audit Metadata