simplified-technical-english
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The main instructions (SKILL.md) direct the AI agent to execute a bundled Python utility (
scripts/ste_check.py) using the shell to validate text compliance. - [INDIRECT_PROMPT_INJECTION]: The skill processes external technical documentation provided by users, creating a surface for indirect instructions.
- Ingestion points: Technical documentation, procedures, and manuals provided by the user as input for rewriting or checking (SKILL.md).
- Boundary markers: The prompt instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the input data.
- Capability inventory: The agent is empowered to execute shell commands to run the internal validation script (
scripts/ste_check.py). - Sanitization: There are no explicit instructions to sanitize or escape user-provided content before it is interpolated into commands or processed for rewriting.
Audit Metadata