The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like ls to browse the local content database and runs python3 agents/post_tweet.py to trigger social media posts.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to getlate.dev for account management and scheduling. This external communication is integral to the skill's social media management purpose.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing external data from podcasts, blogs, and search results without sanitization. Ingestion points: Master Content Database and web searches (SKILL.md). Boundary markers: Absent in sub-agent prompts. Capability inventory: shell command execution, Python script execution, and network API requests (SKILL.md). Sanitization: No data validation or escaping is applied to the ingested content.

x-posting