fireflies-core-workflow-b
Analyze authorized Fireflies meetings with current transcript filters and use AskFred only under explicit AI-credit, privacy, and citation controls. Use when performing scoped discovery or meeting Q&A. Trigger with "search Fireflies meetings", "AskFred analysis", or "query meetings for a topic".
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The agent queries Fireflies meetings and transcripts where meeting participants or speakers may author untrusted transcript text ingested into the workflow.
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.