The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content and context files to generate social media variants, which creates a potential surface for indirect prompt injection attacks.\n
Ingestion points: Data enters the agent's context through the --input and --context arguments of the post_analyzer.py script as described in the Workflow Protocol.\n
Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands within the analyzed text.\n
Capability inventory: The skill is configured with Read and Write tools and executes local Python scripts to perform its workflow.\n
Sanitization: The post_analyzer.py script performs basic string operations (splitting and keyword matching) but lacks sanitization or escaping mechanisms to handle potentially malicious instructions in the input.\n- [COMMAND_EXECUTION]: The skill workflow relies on the execution of local Python scripts, including post_analyzer.py, engagement_optimizer.py, and thread_generator.py. These scripts are invoked via the shell to process marketing data and generate platform-specific optimizations.

social-media-post