ponisha-mcp@0.4.0
CAUTION· install onlyPublisher claims: "Enables AI assistants to search freelance projects, submit and edit bids, read and reply to employer messages, and update a freelancer profile through an unofficial integration." 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: 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
PONISHA_PASSWORDPONISHA_TOKENConfiguration, not credentials: PONISHA_MAX_RESPONSE_CHARS, PONISHA_READ_ONLY, PONISHA_SESSION_DIR, PONISHA_TIMEOUT_MS, PONISHA_USERNAME- Where it talks to
- ponisha.ir (its own)
- 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 PONISHA_PASSWORD, PONISHA_TOKEN and talks to ponisha.ir. 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.
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 2026-11-10 and scored it 76/100 (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; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
"Add a portfolio item («نمونهکار») to your profile. Upload its content files first with ponisha_upload_file " +Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.if (method !== "p" && method !== "s") console.log("Please type only p or s. You'll enter the password on the next step, hidden.");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.import { mkdir, readFile, writeFile, chmod } from "node:fs/promises";Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim kia-karami: 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.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.