The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes untrusted codebase files to drive its instrumentation logic and code modification tasks. \n
Ingestion points: Scans local project files and imports using Read, Grep, and Glob tools to identify languages and frameworks (SKILL.md). \n
Boundary markers: No specific delimiters or instructions are employed to prevent the agent from obeying instructions embedded within the codebase being analyzed. \n
Capability inventory: The skill utilizes Edit, Write, and Bash tools to perform modifications and configure the environment. \n
Sanitization: There is no evidence of sanitization or validation of the codebase content before it influences the agent's actions. \n- [DATA_EXFILTRATION]: The skill interacts with sensitive configuration files such as .env and ~/.opik.config to manage OPIK_API_KEY, OPIK_WORKSPACE, and OPIK_URL_OVERRIDE settings (Step 7). \n- [COMMAND_EXECUTION]: The skill uses Bash for environment discovery and configuration management, although it correctly defers the execution of package installation commands to the user (Step 8).

instrument