writing-clearly-and-concisely
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and edit prose provided by the user or other subagents.
- Ingestion points: Processes user-provided drafts, commit messages, and documentation in files like
SKILL.mdand through subagent workflows. - Boundary markers: The skill recommends using subagents to isolate the processing of specific text drafts.
- Capability inventory: No file writes, network operations, or subprocess calls are present in any of the skill's files.
- Sanitization: No input sanitization is present, but the lack of executable capabilities mitigates the risk of adversarial input.
- [EXTERNAL_DOWNLOADS]: The documentation includes references and links to well-known and trusted informational sources.
- Trusted Sources: References to Project Gutenberg (gutenberg.org), Wikipedia (wikipedia.org), and academic repositories (arxiv.org, aclanthology.org) are used for attribution and illustrative purposes.
- Context: These links are safe and provided to support the skill's educational content.
- [SAFE]: The skill is primarily composed of Markdown documentation and instructional text without associated scripts or executable components.
Audit Metadata