The Agent Skills Directory

[SAFE]: No malicious patterns, credentials, or unauthorized network operations were detected. The skill operates within the expected scope of a business automation tool.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from email bodies and meeting transcripts. This is a characteristic of the skill's intended functionality to summarize external communications.
Ingestion points: Meeting transcripts via get_meeting_transcript and email bodies via gmail_read_thread in SKILL.md.
Boundary markers: Absent. The skill does not instruct the agent to ignore instructions embedded in the retrieved content.
Capability inventory: The agent has capabilities to write files to the revops/customers/ directory and create email drafts via gmail_create_draft as described in SKILL.md.
Sanitization: Absent. There are no instructions to sanitize or escape the content retrieved from external sources before processing it into drafts or local files.

meeting-followup