write-content
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection. * Ingestion points: Fetches content from external links using WebFetch and processes user-provided tweet text as context in SKILL.md. * Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' markers when interpolating external content. * Capability inventory: The skill uses WebSearch and WebFetch for network operations; it does not have file-write or system command execution capabilities across its scripts. * Sanitization: There is no mention of sanitization or filtering for the data retrieved from external sources before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The references/readme-templates.md file contains several URLs to well-known external services for GitHub profile widgets (e.g., shields.io, github-readme-stats.vercel.app, streak-stats.demolab.com). These references are standard for creating developer profile READMEs and originate from reputable domains.
Audit Metadata