Atlas / Skills / jeremylongshore / Fireflies Incident Runbook

Fireflies Incident RunbookBLOCK

skills/jeremylongshore/fireflies-incident-runbook

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
BLOCK
Grade
D
Trust score
69 /100
Version
1.12.0
Hosts
1 documented
License
MIT
Stars
2,823
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: fireflies-incident-runbook
description: >-
  Triage Fireflies auth, privacy, webhook, quota, data exposure, processing, and privileged-mutation incidents with containment and evidence boundaries. Use when responding during a live failure or suspected leak. Trigger with "Fireflies incident", "Fireflies outage", or "Fireflies data leak".
allowed-tools: Read,Glob,Grep,Write,Edit
argument-hint: "<repository-path> <workflow-scope>"
version: 1.12.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags: [saas, fireflies, incident-response, security]
model: inherit
effort: high
compatibility: "Designed for Claude Code; live Fireflies work requires network access"
---
# Fireflies Integration Incident Runbook

## Overview

Triage Fireflies auth, privacy, webhook, quota, data exposure, processing, and privileged-mutation incidents with containment and evidence boundaries.

## Prerequisites

- The target repository or integration path and the requested operator outcome.
- The Fireflies principal, team, environment, and data classification for the work.
- Current Fireflies documentation, credentials only when needed, and an accountable approver.

## Current Contract

Classify incidents by confidentiality, integrity, availability, and destructive impact. Containment may mean disabling a consumer, revoking a key, pausing a queue, rejecting webhooks, or blocking mutations; preserve content-free evidence and coordinate destructive actions.

## Authentication

For authenticated operations, inject `FIREFLIES_API_KEY` from an approved secret manager and send it only as `Authorization: Bearer REDACTED_KEY` to `https://api.fireflies.ai/graphql`. Never print, commit, place in a URL, forward to a browser, or include the key in evidence. Webhook signing secrets are separate credentials and must not be reused as API keys.

## Instructions

1. Declare an owner, severity, affected environment, timeline, and known operation or event family.
2. Contain the smallest boundary: caller, key, webhook endpoint, queue, worker, or mutation feature.
3. Preserve redacted logs, request IDs, GraphQL codes, signature results, deployments, and configuration revisions.
4. Determine whether meeting data, bearer keys, signing secrets, roles, privacy, shares, channels, or deletions were affected.
5. Rotate secrets or disable access only through the accountable owner and record the action.
6. Recover with synthetic or metadata-only probes and bounded traffic.
7. Document root cause, affected records through an approved channel, corrective actions, and follow-up tests.

## Tool Discipline

Use Read, Glob, and Grep to inspect code, configuration, tests, and evidence. Use Write/Edit only for approved implementation or documentation changes. Do not query Fireflies, retrieve meeting content, create an AskFred thread, upload media, change account state, replay an event, or deploy merely because this skill was invoked.

## Approval Boundaries

Require approval before revoking production access, replaying events, restoring data, changing privacy or roles, notifying external parties, or deleting evidence.

## Output

Return the exact operation or event surface, environment, authorization class, selected field groups, validation results, content-free metrics, decisions, and a concise pass/fail receipt. Keep secrets and meeting-derived content out of general output.

## Validation

Before reporting success, rerun the smallest relevant deterministic check, compare actual state with the requested outcome and current contract, verify no secret or meeting-derived content entered logs or artifacts, and record unresolved uncertainty explicitly.

## Error Handling

- Potential secret exposure: prioritize containment and audit over routine debugging.
- Unknown mutation outcome: reconcile state before replay.
- Meeting content appears in a general incident channel: move to the approved restricted process.

## Examples

- "Review fireflies integration incident runbook" produces a bounded plan and redacted receipt.
- A request that widens access or mutates production is paused at the approval boundary.

## Resources

Read [official Fireflies.ai evidence](references/official-docs.md) before relying on a field, filter, event, permission, plan limit, mutation, or processing state.
04

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

CRITICALPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
SKILL.md:33
For authenticated operations, inject `FIREFLIES_API_KEY` from an approved secret manager and send it only as `Authorization: Bearer REDACTED_KEY` to `https://api.fireflies.ai/graphql`. Never print, co
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine

Gates applied: critical_finding, no_behavioural_pass, undeclared_transfer.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__fireflies-incident-runbook.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f83675ca38aBLOCKD69first audit
06

Questions

What does the Fireflies Incident Runbook skill do?

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Is Fireflies Incident Runbook safe to install?

No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.

What can Fireflies Incident Runbook access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does Fireflies Incident Runbook work with?

Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement