The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/configure-keyapi-auth.mjs performs persistent modifications to user shell configuration files, including .bashrc, .zshrc, .bash_profile, .profile, and PowerShell profiles. It appends a managed block to these files to export the KEYAPI_TOKEN environment variable across shell sessions.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion of untrusted Pinterest content. 1. Ingestion points: Pin descriptions, board titles, and user profile data are retrieved through scripts/keyapi-api.mjs. 2. Boundary markers: The skill does not use delimiters or instructions to ignore embedded commands within the retrieved data. 3. Capability inventory: The skill possesses both network communication and file system write access. 4. Sanitization: Pinterest content is interpolated into the agent context without sanitization or filtering to prevent malicious instruction execution.

keyapi-pinterest