The Agent Skills Directory

[SAFE]: The skill provides structured guidance for a 'VP of Sales' persona to perform pipeline reviews. It includes scoring frameworks, risk flag definitions, and diagnostic questions.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill attempts to load context from a local file ('.agents/sales-context.md') to inform its analysis. This is a standard practice for project-specific context and does not involve accessing sensitive system directories or credentials.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from a configuration file and user-provided deal details, it possesses no exploitable capabilities (such as network access, file writing, or command execution) that could be leveraged by malicious content in those inputs.
[REMOTE_CODE_EXECUTION]: No external scripts are downloaded or executed. The skill relies entirely on the model's internal reasoning and the provided markdown instructions.

pipeline-review