The Agent Skills Directory

[PROMPT_INJECTION]: This skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted external data from research papers and code repositories.
Ingestion points: The alpha get command (retrieving ArXiv papers) and alpha code command (reading GitHub repositories) in SKILL.md introduce external content into the agent's context.
Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the retrieved papers or code.
Capability inventory: The skill uses the bash tool to execute alpha and feynman CLI commands, which can perform network and file operations.
Sanitization: No sanitization or filtering of the external content is described before it is provided to the agent.
[COMMAND_EXECUTION]: The skill instructs the agent to interact with the environment via the alpha command-line interface using bash for paper retrieval, search, and annotation management.
[EXTERNAL_DOWNLOADS]: The skill fetches academic papers and source code from well-known platforms including ArXiv and GitHub. These operations are consistent with the skill's primary research purpose.

alpha-research