Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
The canonical home for this skill is debugging in code-yeongyu/lazycodex
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The visible skill is a legitimate debugging methodology with no obfuscation, pretexts, impersonation, or covert triggers, but its macOS network-capture section installs a MITM root CA into the System keychain and changes system proxy settings, and its cleanup list does not explicitly remove that CA.
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 browser-QA workflow drives omowright against a user-selected URL (the app under debug or an arbitrary page the bug involves), so the agent ingests web page content it must actively navigate to rather than content pushed into a monitored feed.
code-yeongyu/oh-my-openagent
687f5af
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.