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, andpackage.json. Boundary markers: No explicit delimiters or instructions to ignore embedded content are present. Capability inventory: UsesRead,Grep,Glob, andWritetools 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