The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscated content were detected across the skill files.- [DATA_EXPOSURE]: The skill instructs the agent to read local project context files (such as .agents/product-marketing.md) to provide relevant advice. This is standard behavior for context-aware agents and does not involve accessing sensitive system credentials or private keys.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests data from external markdown files. However, because the skill lacks capabilities for code execution, network access, or system modification, the risk is negligible and limited to potentially influencing the generated advice.

onboarding