tslj-select
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and organizational logic for content analysis. It does not execute code, access sensitive system files, or perform network operations to untrusted domains.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content such as video transcripts and links provided by the user. While this represents a data ingestion surface, it is inherent to the skill's primary purpose of content analysis.
- Ingestion points: Processes video transcripts, links, and descriptions provided by the user (described in SKILL.md sections I and II).
- Boundary markers: The instructions do not define specific delimiters for separating user-provided transcripts from the agent's internal logic.
- Capability inventory: The skill's capabilities are limited to generating content advice and passing context to other local instruction files (tslj-idea, tslj-open, tslj-script).
- Sanitization: No explicit sanitization or filtering of external text is performed.
Audit Metadata