The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Execute tool to run git commands, specifically git log and git config user.name, to identify the local user and analyze the repository's contribution history.
[DATA_EXFILTRATION]: The skill constructs a sharing link for x.com (Twitter) that includes a summary (pull quote) derived from the repository analysis. This involves sending data derived from the local environment to an external service, though it requires manual user interaction to click and post.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted content from the repository (via Read and Grep) to determine the codebase's 'personality'.
Ingestion points: Files read using Read, Grep, and Glob tools during the scanning phase.
Boundary markers: None identified in the prompt instructions to isolate codebase content from the agent's instructions.
Capability inventory: The skill has access to Execute, Read, Grep, and LS tools.
Sanitization: No specific sanitization or filtering of codebase content is mentioned before it is processed by the LLM.

dating-profile