Find a tool for each step this project still does by hand, and write the picks into CLAUDE.md under `## Tools` for you to review in the diff.
73%
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/stack/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 disclosed and reviewable, but it has the agent write standing instructions into CLAUDE.md that future sessions will run unasked, a persistent behavior the user may not expect, so it is sketchy rather than clearly malicious.
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 `sound:find` subagents that actively search the web and package registries for tools, so outsider-authored pages and registry metadata are read only after the agent chooses to search, which is the low category; the manifests, CI, README, and instruction files it reads are project-owned.
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.