The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a utility script find-polluter.sh that automates test execution using npm test. The script contains potential word-splitting issues in its loop handling of file names, which could lead to unexpected behavior if processing files with special characters or spaces.
[DATA_EXFILTRATION]: Contains instructions to verify the presence of environment variables (e.g., IDENTITY) and keychain identities. The provided patterns use defensive shell expansion (${VAR:+SET}) to check for a variable's existence without printing its value, minimizing accidental exposure of secrets during build environment troubleshooting.
[PROMPT_INJECTION]: The systematic debugging process requires the agent to ingest and analyze external data such as error logs and stack traces. This creates an indirect prompt injection surface where malicious instructions embedded in application logs could attempt to influence the agent's behavior during the root cause investigation phase.

systematic-debugging