writing-clearly-and-concisely

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): Potential for Indirect Prompt Injection (Category 8). The skill is designed to ingest and process untrusted data from external sources.
  • Ingestion points: Processes prose such as pull request descriptions, commit messages, and technical documentation (SKILL.md).
  • Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are provided to separate the prose being edited from the agent's instructions.
  • Capability inventory: Based on the provided file, the skill is limited to text generation and subagent dispatch for copyediting; it lacks high-risk capabilities like arbitrary command execution, network exfiltration, or direct file system writes.
  • Sanitization: No sanitization or validation of the input text is mentioned. The risk remains low as the output is primarily intended for human consumption or agent reasoning without side effects.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 08:53 PM