Skills/PyPI/rishi-ai-mcp

rishi-ai-mcp@1.6.2

VERIFIED· not started

Publisher claims: "Bring the profound wisdom of Vedic Astrology to your AI agents via the Model Context Protocol." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher adarshj322 · publishing for 223 daysInstalls 2,503Last detonated 18 min ago
$claude mcp add rishi-ai-mcp -- uvx rishi-ai-mcp
WatchReport an issue

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 openrouter.ai, opencode.ai — 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.

$vet-skills run --net declared -- uvx rishi-ai-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.3.0

vet-skills diff rishi-ai-mcp 1.3.0 1.6.2

This version reaches for something 1.3.0 did not: 2 new hosts (opencode.ai, openrouter.ai). Compared from the two recorded runs, not from source.

New hosts
opencode.ai, openrouter.ai

1.3.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-16 and scored it 92/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

LOW
Rule modification attemptevals/README.md:165 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file…only) | notes | |---|---|---|---|---|---|---|---| | 2026-11-09 | 74efce7 | 26 | rule 1: SE = sqrt(0.5×0.5/26) = 0.098058; locked gate delta > 0.098058 | with 4/26 = 0.…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Python subprocess execution detectedtools/stamp_commit.py:20 · Python subprocess execution detectedcommit = subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_tier1.py:106 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, timeout=7200, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_plugin_wheel.py:34 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Rule modification attemptevals/README.md:166 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file…he 6000 cap; dashaflow 1.5.1 (Moshier fallback) | | 2026-11-09 | 88e7048 | 26 | rule 1: SE = 0.098058; locked gate delta > 0.098058 | with 3/26 = 0.115 [0.04, 0.2898];…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Python subprocess execution detectedtests/test_build_plugin.py:102 · Python subprocess execution detectedreturn subprocess.run([sys.executable, str(TOOL), *args],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Rule modification attemptevals/results/2026-11-09-pilot/results.json:4209 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file"se_rule": "rule 1: 0.5/sqrt(n)"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Python subprocess execution detectedtools/eval_runner.py:385 · Python subprocess execution detectedreturn subprocess.check_output(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
LOW
Rule modification attemptevals/results/2026-11-09-pilot/report.md:6 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file- SE rule: rule 1: 0.5/sqrt(n)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Python subprocess execution detectedtests/test_plugin_wheel.py:19 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtools/tier1_check.py:86 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Rule modification attemptevals/README.md:168 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file…vals/results/2026-11-09-verdict/CORRECTION.md`. | | 2026-11-10 | 05851ae | 26 | rule 1: SE = 0.098058; locked gate delta > 0.098058 | with 4/26 = 0.154 [0.0615, 0.3353…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Python subprocess execution detectedtests/test_build_plugin.py:154 · Python subprocess execution detectedreturn subprocess.run([sys.executable, str(TOOL), *args],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Rule modification attemptevals/README.md:169 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file… checkpoint; dashaflow 1.5.1 (Moshier fallback) | | 2026-11-10 | b63c7de | 26 | rule 1: SE = 0.098058; locked gate delta > 0.098058 | with 3/26 = 0.115 [0.04, 0.2898];…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Rule modification attemptevals/results/2026-11-09-pilot-glm/report.md:6 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file- SE rule: rule 1: 0.5/sqrt(n)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Rule modification attemptevals/results/2026-11-09-verdict/report.md:8 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file- SE rule: rule 1: 0.5/sqrt(n)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesplugin/skills/rishi-reading/contract.md:11 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…ing a reading under this plugin — the reading model and any host model asked to edit a reading. `AGENTS.md`, `CLAUDE.md`, and `system_prompt.md` point here and never duplicate this file; when they dr…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptevals/results/2026-11-09-verdict/results.json:4220 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file"se_rule": "rule 1: 0.5/sqrt(n)"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Refusal suppressionevals/results/2026-11-09-pilot-glm/results.json:3677 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file"reason": "The response offers remedies \u201ctoday\u201d and never refuses the transaction framing or addresses the money framing.",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Rule modification attemptevals/results/2026-11-09-pilot-glm/results.json:4199 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file"se_rule": "rule 1: 0.5/sqrt(n)",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesskills/rishi-reading/contract.md:11 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…ing a reading under this plugin — the reading model and any host model asked to edit a reading. `AGENTS.md`, `CLAUDE.md`, and `system_prompt.md` point here and never duplicate this file; when they dr…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Rule modification attemptevals/results/2026-11-10-verdict-glm/report.md:6 · Rule modification attempt — overwriting existing instructions · informational: not an instruction file- SE rule: rule 1: 0.5/sqrt(n)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01

Cost to the agent

Instructions loaded
≈5,258 tok
4 files · 80 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

Not checked against OSV yet; the weekly check has not reached this version.