writing-clearly-and-concisely
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, human-written prose such as documentation, commit messages, and reports, which is an ingestion surface for untrusted data. Ingestion points: Instructions in SKILL.md direct the agent to apply rules to any human-read prose. Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined. Capability inventory: The skill specifies copyediting tasks and the use of subagents for processing drafts. Sanitization: No filtering or sanitization of input text is provided.
- [SAFE]: No malicious code, prompt injections, or obfuscated payloads were detected. The reference material provided in elements-of-style.md is a public domain text focusing on English style and grammar.
Audit Metadata