daily-ui-inspiration-capture
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to perform its workflow, including executing a local Node.js script (scripts/check-ui-inspiration-duplicates.mjs) for verification and using Git commands (git status, git add, git commit) to manage the article project files.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and processes content from untrusted external websites to generate descriptions and AI-builder prompts.
- Ingestion points: Live landing pages and UI inspiration sources accessed through the browser (SKILL.md).
- Boundary markers: No explicit delimiters or warnings to ignore instructions within the captured content are defined.
- Capability inventory: The skill has the ability to write files to the local file system, execute local scripts via Node.js, and perform Git repository operations.
- Sanitization: There is no evidence of sanitization or filtering applied to the content scraped from the external websites before it is interpolated into the article content.
Audit Metadata