afr@0.1.0
VERIFIED· not startedPublisher claims: "This MCP server exposes an agent flight-recorder's verified experience store to coding agents, letting them search recorded task attempts, evidence-backed lessons, and provenance for prior failures before repeating mistakes. It combines hybrid BM25+dense retrieval with applicability checks so agents can retrieve what actually worked on similar problems." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso claude.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-12 and scored it 85/100 (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 · 2 scenarios · 0 deviationsStatic findings
subprocess.run(["git", *cmd], cwd=proj, check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."kill the stale dev server on port 3000",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.episode("d3", 20, "KeyError: 'DATABASE_URL'", "copy .env.example"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run(["git", *args], cwd=cwd, capture_output=True, timeout=GIT_TIMEOUT_S, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.episode("mine", 0, "KeyError: 'DATABASE_URL'", "export DATABASE_URL in .env"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.check = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.subprocess.run(["git", "commit", "-qam", "fix config"], cwd=proj, check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(argv, cwd=cwd, capture_output=True, text=True, timeout=timeout_s, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.p = subprocess.run(TEST_CMD, cwd=cwd, capture_output=True, text=True, timeout=60, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.load(app, episode("x1", 0, f"PermissionError: denied {SECRET}", "chmod +x scripts/run.sh"))Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.subprocess.run(["git", *cmd], cwd=proj, check=True, capture_output=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."url": f"git clone https://alice:{fakes.URL_PASSWORD}@example.com/repo.git",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run([sys.executable, str(ROOT / "benchmarks/build_corpus.py")], check=True, capture_output=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.