writing-clearly-and-concisely
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied prose for editing and rewriting tasks, which creates a potential surface for indirect prompt injection. However, the risk is negligible as the skill lacks exploitable capabilities. 1. Ingestion points: User-provided text (as described in SKILL.md). 2. Boundary markers: Absent; the skill does not define specific delimiters for user data. 3. Capability inventory: None; the skill does not include any scripts or tool invocations that could be abused (confirmed via analysis of all files). 4. Sanitization: Absent; the skill relies on the agent's internal guardrails.
- [NO_CODE]: The skill consists entirely of Markdown instructional content. No executable scripts, binary files, or configuration files for software dependencies were identified during the audit.
- [SAFE]: The skill documentation includes numerous references to external resources, all of which point to reputable academic, news, or community-driven websites such as Wikipedia, ArXiv, and major news outlets. No indicators of obfuscation, credential exposure, or unauthorized data access were found.
Audit Metadata