Investiga sistemas distribuidos e artefatos por engenharia reversa autorizada. Trigger em: "analisar binário", "decompilar APK", "inspecionar ASAR", "analisar app Electron sem código-fonte", "inspecionar firmware", "browser sem código-fonte", "reverse engineer this binary", "comparar versões compiladas", "rea-agents", "usar REA", "REA MCP", "engenharia reversa de binário", "engenharia reversa de aplicativo distribuído".
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required runtime path can ingest arbitrary web page text (accessibility text, console, scripts, and page content) from a user-opened browser or Electron page via CDP, and HAR/mitmproxy captures of web traffic, which outsiders can author. The agent must select and capture these pages, so outsiders cannot force delivery and the risk is low.
felvieira/claude-skills-fv
b0cbfa3
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.