The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple external Python scripts to facilitate its workflow, including posting-time-analyzer.py, hashtag-analyzer.py, brand-voice-scorer.py, approval-manager.py, and execution-tracker.py. These scripts perform content analysis and manage the scheduling state.
[DATA_EXFILTRATION]: The skill is designed to transmit user-provided text, media assets, and tracking parameters to external social media APIs (Twitter/X, Instagram, LinkedIn, TikTok, YouTube, and Pinterest) through Model Context Protocol (MCP) servers.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted user input to generate content variations.
Ingestion points: User-supplied 'Post content' and 'Hashtags' used in formatting and variation steps.
Boundary markers: No explicit markers or instructions are provided to the agent to treat input as data rather than instructions.
Capability inventory: The agent has the ability to execute subprocesses (Python scripts), write to the local file system (~/.claude-marketing/), and perform network operations via MCP servers.
Sanitization: There is no evidence of sanitization or validation of the input content before it is interpolated into prompts or sent to external platforms.

schedule-social