fish-story@0.4.1
VERIFIED· not startedPublisher claims: "Enables AI agents to play and manage local interactive story sessions through MCP tools, including starting games, viewing scenes and choices, recording decisions, pausing/resuming, branching saves, and exporting play experiences." 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
LLM_API_KEYConfiguration, not credentials: FISH_PLAYER_ID, FISH_STORY_HOME, LLM_BASE_URL, LLM_MODEL, SystemRoot- Where it talks to
- no vendor host named in the codeAlso creativecommons.org, python.org — 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 with a scoped credential, under the guard, and read the third-party hosts first. The code names creativecommons.org, python.org as well as its own vendor. The guard injects LLM_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
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 83/100 (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
'session.json', 'saves', 'sessions', '.env'))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.if any(p in BLOCKED for p in parts) or path.suffix.lower() in {'.sqlite', '.db', '.key', '.log'} or path.name.startswith('.env'):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run([str(executable), '--home', str(home), *arguments],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.output = subprocess.run(['git', 'ls-files', '--cached'], cwd=ROOT, check=True, capture_output=True, text=True).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.if path.suffix.lower() in {'.db', '.sqlite', '.sqlite3', '.key', '.log'} or path.name.startswith('.env'):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run([sys.executable, '-m', 'fish_story.cli', '--home', str(tmp_path), *args],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([str(powershell), '-NoProfile', '-ExecutionPolicy', 'Bypass', '-File',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.help_proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.('project-main/.env', 'PRIVATE_FILE_NOT_COPIED'),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.memory = subprocess.run([str(executable), '--home', str(home), 'export', sid, '--format', 'memory'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, '-m', 'PyInstaller', '--noconfirm', *clean,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.version_proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen([str(desktop), '--home', str(home), 'serve', '--port', '0'],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.load_dotenv(Path(__file__).resolve().parents[1] / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<label>读取 Markdown / 纯文本<input id="core-file" type="file" accept=".md,.txt,text/plain,text/markdown"></label><label>最终导入内容,可直接编辑<textarea id="core" rows="7" plaFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Private state defaults outside this checkout. Do not stage `.env`, core files,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.version_proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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.