The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the processing of untrusted meeting transcripts.
Ingestion points: Meeting transcripts and summaries are retrieved using the fireflies_get_transcript and fireflies_get_summary tools as described in SKILL.md.
Boundary markers: The instructions do not define delimiters or specific guardrails to prevent the agent from following malicious instructions that might be embedded within the transcript text.
Capability inventory: The skill possesses the capability to perform email searches and create drafts via gmail_search and gmail_create_draft (SKILL.md).
Sanitization: There is no evidence of content sanitization or validation performed on the transcript data before it is used to generate email drafts.

meeting-followup