Skills/npm/pi-multi-agent-skill

pi-multi-agent-skill@0.2.1

CAUTION

Publisher claims: "A minimal multi-agent skill+cli for pi. It adds no extension or tools, so it uses only a few dozen tokens of the context window until the main agent delegates, yet it gives the same controls as a subagent extension. Background agents keep running after th" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher milanglacier · joined 2 days agoInstalls 704Last detonated 1 h ago

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 79/100 (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. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionskills/multi-agent/scripts/multi_agent.py:721 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/multi-agent/SKILL.md:115 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/multi-agent/SKILL.md:106 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedskills/multi-agent/scripts/multi_agent.py:1417 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Hidden zero-width characters detectedskills/multi-agent/scripts/multi_agent.py:344 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandskills/multi-agent/scripts/multi_agent.py:110 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedskills/multi-agent/scripts/multi_agent.py:863 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandskills/multi-agent/scripts/multi_agent.py:2021 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/multi-agent/scripts/multi_agent.py:1877 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,360 tok
1 file · 15 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for pi-multi-agent-skill@0.2.1 as of 44 min ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim milanglacier: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  3. 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.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim milanglacierPropose a patch to the maintainer