writing-clearly-and-concisely

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-supplied text (such as documentation drafts and commit messages) to improve its clarity and style. While the skill itself does not contain malicious code, it establishes a processing pipeline for external data without explicit instructions for the agent to use boundary markers or sanitization, creating a surface for potential indirect prompt injection attacks.
  • Ingestion points: User-provided prose drafts processed via the instructions in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within user text.
  • Capability inventory: The skill operates within the agent's default environment, which may include tools for file system access and shell execution.
  • Sanitization: No sanitization or filtering logic is provided for the external content before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:04 PM
Security Audit — agent-trust-hub — writing-clearly-and-concisely