The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script node tooling/scripts/teaching-sweep.mjs <API name> as part of the repair workflow. The <API name> argument is sourced from user input, which could be exploited for command injection if the execution environment does not adequately sanitize shell arguments.- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the project environment, which could contain malicious instructions. Ingestion points: The skill reads VISION.md, source code files (types, exports), and user-supplied $ARGUMENTS. Boundary markers: There are no explicit instructions or delimiters to distinguish between data and agent instructions. Capability inventory: The skill is capable of modifying files (VISION.md, docs, examples) and executing shell scripts. Sanitization: No sanitization or validation of the ingested content is specified.

best-api