The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes local Node.js scripts, specifically node scripts/run-state-check.js and node skills/write/scripts/lint.js, to perform data checks and linting on drafts. These paths refer to local scripts within the repository environment.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it is designed to ingest and process data from external, potentially untrusted sources. 1. Ingestion points: External data is ingested from pull requests, issues, user quotes, and experiment results (SKILL.md). 2. Boundary markers: The skill does not employ boundary markers or instructions to delimit or ignore embedded commands within the source data. 3. Capability inventory: The skill has the capability to execute shell commands using the node environment (SKILL.md). 4. Sanitization: There are no explicit sanitization or validation steps described for the external content before it is interpolated into the drafting process.

content