Claude Code, Plugin
confidence
Access Confidence feature flags, experiments, and migration tools directly from Claude Code.
Compatibility: Portable across standard formats.
Grade B
Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit ba96f74234db, unchanged since the check below.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST SECRETS_PATH_DOTENV OBFUSCATION_ENCODED_BLOB PERMISSION_SHELL_DECLARED SECRETS_ENV_READ
Why this grade
- NETWORK_NO_FIXED_HOST Low
Makes a network call whose host is not written as a fixed address.
evals/lib/scorers/onboard-judges.ts, line 18
(like createFlag or getIdentityInfo) or curl commands in prose, mention of telemetry, - NETWORK_UNNAMED_HOST Low
Calls a fixed host that the description does not name.
evals/lib/scorers/onboard-judges.ts, line 18
(like createFlag or getIdentityInfo) or curl commands in prose, mention of telemetry, - SECRETS_PATH_DOTENV Low
Mentions a .env file.
skills/analyze-project/SKILL.md, line 569
- [ ] Check that `.env` is in `.gitignore` (so the secret stays out of git) - OBFUSCATION_ENCODED_BLOB Low
Contains a long base64 shaped string in a file that should be readable.
skills/migrate-optimizely/SKILL.md, line 1
--- - PERMISSION_SHELL_DECLARED Note
Runs shell commands, and the manifest or description says so.
skills/onboard-confidence/auth.py, line 80
subprocess.Popen(['open', authorize_url]) - SECRETS_ENV_READ Note
Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.
skills/instrument-events/SKILL.md, line 385
clientSecret: process.env.CONFIDENCE_CLIENT_SECRET!,
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
skills/onboard-confidence/auth.py, line 80
subprocess.Popen(['open', authorize_url])
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Concern
can reach a host that is not written as a fixed address. can reach onboarding.confidence.dev. The description does not name that host. can reach events.eu.confidence.dev. The description does not name that host. can reach iam.confidence.dev. The description does not name that host. can reach flags.confidence.dev. The description does not name that host. can reach events.. The description does not name that host. can reach konfidens.eu.auth0.com. The description does not name that host. can reach
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
evals/lib/scorers/onboard-judges.ts, line 18
(like createFlag or getIdentityInfo) or curl commands in prose, mention of telemetry,
evals/lib/scorers/onboard.ts, line 92
"curl ",
evals/multi-turn/instrument-events-scores.ts, line 71
- curl commands or API endpoints
Show more
evals/multi-turn/scores.ts, line 72
like createFlag or getIdentityInfo, no curl commands, and no mention of telemetry.
skills/analyze-project/SKILL.md, line 27
curl -s -X POST "https://onboarding.confidence.dev/v1/agentTelemetryKey:acquire" \
skills/analyze-project/SKILL.md, line 45
curl -s -X POST "https://events.eu.confidence.dev/v1/events:publish" \
skills/instrument-events/SKILL.md, line 28
curl -s -X POST "https://onboarding.confidence.dev/v1/agentTelemetryKey:acquire" \
skills/instrument-events/SKILL.md, line 39
curl -s -X POST "https://events.eu.confidence.dev/v1/events:publish" \
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
skills/analyze-project/SKILL.md, line 551
- `<.env file>` - added `CONFIDENCE_CLIENT_SECRET`
skills/analyze-project/SKILL.md, line 569
- [ ] Check that `.env` is in `.gitignore` (so the secret stays out of git)
skills/instrument-events/SKILL.md, line 385
clientSecret: process.env.CONFIDENCE_CLIENT_SECRET!,
Show more
skills/instrument-events/SKILL.md, line 400
flagClientSecret: process.env.CONFIDENCE_CLIENT_SECRET!,
skills/migrate-eppo/test-fixtures/phase2-examples/go-server/main.go, line 41
clientSecret := os.Getenv("CONFIDENCE_CLIENT_SECRET")
skills/migrate-eppo/test-fixtures/phase2-examples/nextjs-precomputed/migration-plan.md, line 60
flagClientSecret: process.env.CONFIDENCE_FLAG_CLIENT_SECRET!,
skills/migrate-eppo/test-fixtures/phase2-examples/nextjs-precomputed/src/components/FeatureFlagTest.tsx, line 6
const flagKey = process.env.NEXT_PUBLIC_EPPO_FLAG_KEY;
skills/migrate-eppo/test-fixtures/phase2-examples/nextjs-precomputed/src/lib/confidence.ts, line 5
flagClientSecret: process.env.CONFIDENCE_FLAG_CLIENT_SECRET!,
skills/migrate-optimizely/test-fixtures/seed_optimizely.py, line 177
token = os.environ.get("OPTIMIZELY_API_TOKEN", "")
skills/migrate-optimizely/test-fixtures/phase2-examples/node-decide-server/src/server.js, line 5
sdkKey: process.env.OPTIMIZELY_SDK_KEY,
skills/analyze-project/SKILL.md, line 454
- Call `mcp__confidence-flags__getClientSecret` and write it to `.env` as `CONFIDENCE_CLIENT_SECRET`.
skills/analyze-project/SKILL.md, line 458
- Create/update `.env` with `CONFIDENCE_CLIENT_SECRET=<your-client-secret-here>` as a placeholder.
skills/analyze-project/SKILL.md, line 459
- Print: "Create a client at https://app.confidence.spotify.com and paste its secret into .env"
skills/analyze-project/SKILL.md, line 461
If `.gitignore` exists and doesn't list `.env`, add it.
skills/instrument-events/SKILL.md, line 197
**Write the secret to `.env`:**
skills/instrument-events/SKILL.md, line 198
- If `.env` exists, append `CONFIDENCE_CLIENT_SECRET=<secret>` (don't overwrite existing vars)
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Concern
contains an encoded blob in a file that should be readable.
OBFUSCATION_ENCODED_BLOB
skills/migrate-optimizely/SKILL.md, line 1
---
assets/logo.svg, line 2
<image width="400" height="400" xlink:href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAGQCAYAAACAvzbMAAAVWUlEQVR4Ae3dvX4TWZoH4JeeCTYbdzYZ4gqAbLI2WW9kd7Yb2VwBcAWYaCcDotkMyD
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit ba96f74234db. requests shell access. The manifest names this permission. can reach a host that is not written as a fixed address. can reach onboarding.confidence.dev. The description does not name that host. can reach events.eu.confidence.dev. The description does not name that host. can reach iam.confidence.dev. The description does not name that host. can reach flags.confidence.dev. The description does not name that host. can reach events.. The description does not name that host. can reach konfidens.eu.auth0.com. The description does not name that host. can reach reads a credential or environment file. contains an encoded blob in a file that should b
Date and source
Date checked:
github.com
Commit graded: ba96f74234db404e87619d885020ac6d46dad907
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.