The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the prowler command-line tool to perform cloud environment audits. The commands provided in the syntax section follow standard security auditing practices for defined profiles and projects.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes data from external cloud provider environments. 1. Ingestion points: The agent reads and analyzes findings generated by the prowler tool output (SKILL.md). 2. Boundary markers: There are no explicit delimiters defined in the procedure to separate potentially untrusted resource names or metadata from the agent's instructions. 3. Capability inventory: The agent has the capability to execute shell commands (prowler CLI) based on its analysis. 4. Sanitization: The skill does not explicitly describe sanitization or filtering of the audit data before processing.

prowler