The Agent Skills Directory

[SAFE]: The installation script ('scripts/install_agent_workspace_rules.py') and the validation script ('scripts/validate_agent_workspace.py') perform standard file management and integrity checks. The use of 'chmod' is restricted to making the skill's own validator script executable. No network operations or access to sensitive system paths were identified.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process 'Source Material' (external markdown, code, and text) to create and update Agent Documents. While this creates a potential surface for indirect prompt injection if malicious instructions are embedded in the ingested data, the skill emphasizes fidelity and incorporates manual human review checkpoints within its workflows. The capabilities are limited to local file system operations within the designated '.agents/' directory, and no automated execution of processed content was detected.

chrisai-knowledge