The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests news content from external sources which is then interpolated into sentiment analysis prompts. This creates a surface where malicious instructions hidden in news articles could potentially influence agent behavior.\n
Ingestion points: news content retrieved from the daily_news and search_detail tables in scripts/database_manager.py.\n
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompt template in SKILL.md.\n
Capability inventory: The agent has access to tools that can write to the database and execute arbitrary SQL queries via scripts/database_manager.py.\n
Sanitization: No explicit sanitization of input text is performed before it is passed to the LLM.\n- [EXTERNAL_DOWNLOADS]: Fetches pre-trained BERT models from Hugging Face's official model hub using the transformers library when local versions are missing.\n- [COMMAND_EXECUTION]: Provides the agent with the ability to execute arbitrary SQL statements against a local SQLite database file through the execute_query method in scripts/database_manager.py.

alphaear-sentiment