technical-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): The skill instructions define a specialized technical writer persona and stylistic constraints. No patterns typical of instruction overrides, system prompt extraction, or safety filter bypasses were detected.
- DATA_EXFILTRATION (SAFE): There are no network operations (curl, fetch, etc.) or access to sensitive local file paths (e.g., credentials, ssh keys). The skill operates entirely on the provided documentation context.
- REMOTE_CODE_EXECUTION (SAFE): No remote scripts or external packages are downloaded or executed. The skill does not use any package managers or remote fetching tools.
- COMMAND_EXECUTION (SAFE): The skill lacks instructions or tools for executing system commands, shell scripts, or binary files.
- OBFUSCATION (SAFE): The markdown and configuration files are written in clear, readable text. No Base64, zero-width characters, or homoglyph-based obfuscation techniques were identified.
- INDIRECT_PROMPT_INJECTION (SAFE): While the skill is designed to ingest and validate external documentation files (READMEs, API docs), it lacks dangerous capabilities such as file writing, network calls, or dynamic code execution. The risk of an injection influencing downstream system state is negligible.
Audit Metadata