mcp-server@1.0.59
VERIFIED· install onlyPublisher claims: "MCP server for DeerDawn — AI session memory that briefs every new AI session" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
ENV_SECRET_SUFFIXMAX_SECRETConfiguration, not credentials: CLAUDE_PROJECT_DIR, DEERDAWN_HOME, DEERDAWN_SURFACE_ID, DEERDAWN_WORKSPACE, PATHEXT- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard. It asks for ENV_SECRET_SUFFIX, MAX_SECRET and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 1.0.58
vet-skills diff mcp-server 1.0.58 1.0.59This version reaches for something 1.0.58 did not: 2 new credential variables (ENV_SECRET_SUFFIX, MAX_SECRET). Compared from the two recorded runs, not from source.
- New credential variables
- ENV_SECRET_SUFFIX, MAX_SECRET
1.0.58 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
…s first), and, when Codex is installed and the folder has a project, whether to add DeerDawn's block to the repo's `AGENTS.md`. Run with no terminal (by an agent, in a script), every answer is no. It ends …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.var HOOK_RUNNER = `npx -y --prefer-offline ${HOOK_PACKAGE_SPEC}`;Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.