The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the uv run command to interface with a local CLI tool (paper-search) for searching and processing academic papers. This is the primary intended functionality of the skill.
[CREDENTIALS_UNSAFE]: The documentation identifies several environment variables (e.g., PAPER_SEARCH_MCP_CORE_API_KEY, PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY) for providing optional API keys. No hardcoded credentials or secrets are present in the code, adhering to standard security practices.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it extracts and processes text from external academic sources via the read command.
Ingestion points: Content extracted from external sources by paper-search read as described in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are specified in the workflow.
Capability inventory: The agent can execute local commands via uv run and perform network operations through the CLI tool.
Sanitization: No explicit sanitization or filtering of the extracted text content is mentioned.

paper-search