The Agent Skills Directory

[SAFE]: The skill acts as a utility for auditing and reviewing the code quality of other AI agent skills, following a transparent and logical workflow based on official guidelines. It does not contain obfuscation, hidden instructions, or malicious intent.
[COMMAND_EXECUTION]: The skill instructs the agent to use standard Unix utilities such as ls, head, grep, and cat to analyze the structure and content of skill files. These operations are essential for the stated auditing purpose and are used in a controlled manner.
[EXTERNAL_DOWNLOADS]: The skill's documentation mentions the molthub package as an example of a utility used to install and manage skills for review. This is an informational reference to a community tool.
[PROMPT_INJECTION]: The skill processes untrusted instructions from external SKILL.md files, which presents a surface for indirect prompt injection. 1. Ingestion points: Reads external skill files via cat and head commands. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat audited content as untrusted data. 3. Capability inventory: The skill has the ability to execute shell commands for file system inspection and pattern matching. 4. Sanitization: No specific validation or sanitization is performed on the content of audited skills before processing.

skill-reviewer