The Agent Skills Directory

[SAFE]: The skill follows security best practices, particularly regarding data privacy and credential management. It includes explicit instructions to avoid collecting PII or raw credentials and provides clear guidelines for handling potentially sensitive diagnostic data.
[DATA_EXPOSURE]: The instructions contain strong privacy protections, directing the agent to never ask for raw email, phone numbers, cookies, or device IDs. It also mandates that API tokens retrieved during troubleshooting must be redacted and never exposed to the user.
[COMMAND_EXECUTION]: The skill uses a localized script to interact with Spotify's own API infrastructure. This is appropriate for the skill's purpose and does not involve arbitrary command execution or risky system-level operations.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external implementation evidence (such as GTM exports or site HTML), it provides instructions for read-only audits and sanitization, which effectively mitigates risks associated with untrusted data ingestion.
[PROMPT_INJECTION]: No evidence of prompt injection attempts or bypass instructions were found. The language used is professional and focused on measurement triage and diagnostic procedures.

measurement-debug