Use when you or the user are about to pick a tool, library, framework, CLI or app for a need, before naming one from memory, or when asked to find one.
70%
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
Fix and improve this skill with Tessl
tessl review fix ./sound/skills/find/SKILL.mdDetected 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 skill is a legitimate tool-finding workflow with no sign of intent to attack the user, but its first source runs an unvetted `npx` package, which conflicts with its own "never npx" rule and is a careless, risky step rather than a malicious one.
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 workflow runs GitHub `gh api` reads, and the (b) author check requires judging a repo's issue answers, which is outsider-authored issue text the agent ingests without a specific item being chosen first, so the risk is medium under the GitHub issue-reading rule, with MCP, Hacker News, registry, and web-search results as low-risk search sources.
saadshahd/moo.md
2a844a8
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.