The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes shell commands such as cat and sed to read local project files and a specific Python command to interface with a Google Drive MCP integration script located at /home/podhi/.openclaw/workspace/integrations/google-drive-mcp/upload.js.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it is designed to ingest and process data from external, untrusted sources including tweets and community threads summarized in OPENCLAW_THREADS_DIGEST.md. * Ingestion points: OPENCLAW_THREADS_DIGEST.md and external URLs defined in source manifests. * Boundary markers: Absent; the skill does not use delimiters to isolate external content from the agent's instructions. * Capability inventory: Includes file reading and execution of local Python/JS scripts. * Sanitization: Absent; no validation or filtering of ingested data is specified before synthesis into output guides.

openclaw-guide-synthesis