The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the tessl CLI (e.g., npx tessl skill review) to perform automated auditing of other skills. This execution is legitimate and essential for the skill's primary function of quality assessment.
[EXTERNAL_DOWNLOADS]: The skill references the tessl package from the npm registry, which is a well-known service for software dependencies. This is a standard developer workflow for running CLI utilities.
[SAFE]: The skill does not contain any detected prompt injections, hardcoded credentials, or obfuscated content. It follows progressive disclosure principles by moving dense documentation and rubrics into separate reference files, reducing the surface area for errors during skill execution.
[SAFE]: While the skill audits external data (other skill files), it provides structured review templates and specific instructions to maintain focus on the audit task, which helps mitigate potential risks associated with processing untrusted documentation content.

skill-audit