The Agent Skills Directory

[COMMAND_EXECUTION]: The skill guides the agent to execute vendor-specific CLI commands, including apiiro risks remediate and apiiro guardian query, to perform security remediation tasks.
[PROMPT_INJECTION]: The skill instructions create an indirect prompt injection surface by directing the agent to take content from tool outputs (remediation prompts or AI guidance) and apply it directly as code changes. * Ingestion points: Output from the apiiro risks remediate and apiiro guardian query commands referenced in SKILL.md. * Boundary markers: None identified; the instructions suggest the agent apply fix prompts directly if the is_prompt flag is true. * Capability inventory: The agent is expected to perform code modifications based on the external input received from the CLI. * Sanitization: No explicit sanitization, validation, or human-in-the-loop verification of the external guidance is mentioned in the skill workflow.

apiiro-fix