The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to audit user-provided project files for UX and performance issues. This creates a surface where malicious instructions embedded in the audited code could be ingested into the agent's context.
Ingestion points: The scripts/mobile_audit.py script and the Read/Glob/Grep tools access files within user-specified project paths.
Boundary markers: The skill does not provide specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the files it audits.
Capability inventory: The skill utilizes Bash for running the audit script and standard file-reading tools.
Sanitization: No sanitization or validation of the content read from external files is performed before it is processed by the analysis logic.
[COMMAND_EXECUTION]: The skill includes a local Python script (scripts/mobile_audit.py) intended to be executed via Bash. While the script performs benign static analysis using regular expressions, the SKILL.md file contains a prompt instructing the agent to 'don't read, just run' the script. This encourages a reduction in user/agent oversight, although the script itself is verified as safe functionality provided by the author.

mobile-design