Skills
skills/team-attention/hoyeon/dev-scan/Gen Agent Trust Hub

dev-scan

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python and Node.js scripts (hn-search.py, ph-search.py, and web-search.mjs) to automate data collection. It also utilizes the chromux CLI for browser-based searching and content enrichment.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from well-known technology platforms and APIs, including Algolia (Hacker News), ProductHunt (GraphQL API), and Google. These interactions are limited to public data retrieval for synthesis and reporting.
  • [PROMPT_INJECTION]: While the skill processes untrusted content from various developer communities (a surface for indirect prompt injection), it lacks high-risk capabilities—such as file modification or sensitive network access—that would be necessary to exploit such an injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — dev-scan