solo-video-promo

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from project files to generate video scripts. Ingestion points: docs/prd.md, README.md, CLAUDE.md, and package.json. Boundary markers: No explicit delimiters or instructions to ignore embedded content are present. Capability inventory: Uses Read, Grep, Glob, and Write tools to process local files and store the generated plan. Sanitization: No sanitization or validation of the input file content is performed before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:43 PM