tallyqueue@r1
CAUTION· install onlyPublisher claims: "Enables AI clients to add receipts and invoices with extracted facts and proposed bookkeeping entries, list and update pending items, and retrieve the user's account list over MCP." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 10 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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: Caution 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
TALLYQUEUE_TOKENConfiguration, not credentials: DATA_DIR, MAX_RECEIPT_BYTES, PUBLIC_URL, RIKSBANK_LOOKUP, SOURCE_URL, TALLYQUEUE_RELOAD, TALLYQUEUE_USERS- Where it talks to
- no vendor host named in the codeAlso riksbank.se — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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, and read the third-party hosts first. The code names riksbank.se as well as its own vendor. The guard injects TALLYQUEUE_TOKEN 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 tallyqueue@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
line = line.strip().lstrip('')Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# live here, so a dev stack never uses the real values in .env or the real data volume.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.SITE_ADDRESS: ${SITE_ADDRESS:-${PUBLIC_URL:?Set PUBLIC_URL in .env}}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'#FLAGGA 0\n'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.&& mkdir -p /data && chown app /dataFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.&& rm -rf /var/lib/apt/lists/* \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.env = {k: v for k, v in os.environ.items() if k != 'TALLYQUEUE_USERS'}Fix: Never read or enumerate credential locations; accept a documented environment variable instead.<summary>Delete this item</summary> <form method="post" action="/items/{{ item.id }}/delete" class="stack"> <input type="hidden" name="csrf" value="{{ session.cFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.assert fetch('POST', '/upload', b'MZ\x90\x00\x03\x00\x00\x00', {'X-API-Key': ALICE})[0] == 400Fix: 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. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim gothenburgoffice: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.