simplified-technical-english
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted text (such as PR descriptions, commit messages, and UI copy) to rewrite it into a specific technical style. While this creates an ingestion surface for indirect instructions, the skill defines no executable tools, network capabilities, or file system write access that could be leveraged for an attack. The output is intended for human-reviewed documentation and UI copy.
- Ingestion points: User-provided technical text inputs (PRs, commits, UI copy).
- Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the processed text.
- Capability inventory: The skill does not define or utilize any subprocess calls, network operations, or privileged tools.
- Sanitization: Not applicable as the skill's purpose is purely stylistic text transformation for human consumption.
- [SAFE]: The skill contains no code, scripts, or automated tool invocations. It is a collection of markdown-based guidelines. The external reference to the ASD-STE100 official documentation (asd-ste100.org) is a standard reference to an industry-recognized technical writing specification.
Audit Metadata