The Agent Skills Directory

[NO_CODE]: The entire skill package consists of Markdown files (SKILL.md and the references/ directory) and a JSON evaluation file. No executable code, such as Python or Shell scripts, is present.
[PROMPT_INJECTION]: The instructions are strictly limited to the role of a revenue operations expert. There are no patterns suggesting attempts to bypass safety filters, extract system prompts, or override agent constraints.
[DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file access or network operations are present. The skill uses benign placeholders like [Contact Name] or {Lead.Name} for template demonstration purposes and refers to standard platform context files (e.g., .agents/product-marketing.md).
[REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic execution patterns were identified. The automation 'playbooks' provided are textual configuration recipes for third-party platforms, not code for the agent to execute.

revops