The Agent Skills Directory

[SAFE]: The skill performs static analysis of local shell scripts to improve infrastructure reliability. It explicitly states that scripts are never executed during the audit process to prevent accidental data loss or side effects. The analysis is limited to pattern matching for best practices such as error handling, logging, and concurrency control.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it reads and processes the contents of external shell scripts which could contain malicious instructions designed to influence the agent's report.
Ingestion points: The skill reads files from common script directories like scripts/, cron/, jobs/, and bin/ using the Read tool.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating script content into the analysis prompt.
Capability inventory: The skill has access to Bash, Read, Grep, and Glob tools.
Sanitization: There is no mention of sanitizing or escaping the content of the audited scripts before processing.

cron-job-auditor