The Agent Skills Directory

[DATA_EXFILTRATION]: The skill transmits research queries to api.parallel.ai and openrouter.ai using user-provided API keys. This network activity is authenticated, documented, and restricted to the tool's research functionality. No unauthorized harvesting of sensitive local files or environment secrets was detected.
[COMMAND_EXECUTION]: The skill provides Python-based CLI tools for performing research lookups and instructs the agent to save results to a local sources/ directory for persistence and auditing. These operations are intended for user-controlled research workflows and follow best practices for reproducibility.
[EXTERNAL_DOWNLOADS]: Dependencies are limited to standard, reputable Python packages including requests and openai. No patterns involving the download or execution of unverified remote scripts or runtime binary binaries were identified.
[PROMPT_INJECTION]: The skill processes external research data, which presents a typical surface for indirect prompt injection. Ingestion points: External API responses retrieved in research_lookup.py. Boundary markers: None identified in the prompt templates. Capability inventory: The skill manifest declares access to Read, Write, Edit, and Bash tools. Sanitization: No explicit content sanitization of retrieved research results was found in the data processing logic.

alterlab-research-lookup