tslj-script
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied materials, reference viewpoints, and writing samples to generate or modify scripts.
- Ingestion points: User-provided facts, materials, and reference content described in the 'Workflow' section of
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the external content being processed.
- Capability inventory: Accesses local reference files, executes a local Python script (
scripts/ai_tell_linter.py), and performs text generation. - Sanitization: No explicit sanitization or validation of the user-provided data is mentioned.
- [COMMAND_EXECUTION]: The skill instructs the agent to run a local Python script,
scripts/ai_tell_linter.py, to analyze the generated script's tone and quality. This script appears to be a local utility provided by the skill author.
Audit Metadata