Claude Code, Skill
Sno Station Skills
Copy this prompt into your agent's chat:
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL
Why this grade
- INSTALL_REMOTE_SCRIPT Medium
Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).
README.md, line 26
sh -c 'sno_installer_body=$(curl -fsSL https://sno.ai/install) && printf "%s\n" "$sno_installer_body" | sh' - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/login-in-place.test.ts, line 37
writeFileSync(join(config.claude_home, '.credentials.json'), '{"claude":"token"}');
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/text-check.py, line 38
done = subprocess.run([binary, *path.split(), "--help"], capture_output=True, text=True, timeout=60,
skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/text-check.py, line 61
text_of_path = help_of(path) if path else subprocess.run([binary, "--help"], capture_output=True, text=True,
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.sh, line 232
result = subprocess.run(
Show more
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.sh, line 254
result = subprocess.run(["sno", "reach", "seats", "--json"],
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.sh, line 548
proc = subprocess.run(["ps", "-eo", "pid,ppid,args", "--no-headers"],
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster.sh, line 125
result = subprocess.run(["sno", "reach", "export", "--work", journey,
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster.sh, line 233
rc = subprocess.run(["bash", cw, "verdict", "--journey", journey],
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo.sh, line 677
proc = subprocess.run(["git", "-C", REPO, "cat-file", "-e", spec],
Install and update
Serious
install fetches a script from the network.
INSTALL_REMOTE_SCRIPT
README.md, line 26
sh -c 'sno_installer_body=$(curl -fsSL https://sno.ai/install) && printf "%s\n" "$sno_installer_body" | sh'
Network
Concern
can reach a host that is not written as a fixed address. can reach api.github.com. The description does not name that host.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/no-network.test.ts, line 73
`const s = net.connect({ host: '192.0.2.1', port: 80 });`,
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/docker-env-doctor.sh, line 46
for tool in docker jq grep curl find date flock mktemp ss; do
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/docker-env-doctor.sh, line 269
probe_addr() { # map a bind address to something curl can reach
Show more
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/docker-env-doctor.sh, line 277
HTMP=$(mktemp); HTTP=$(curl -s -m 3 -o "$HTMP" -w '%{http_code}' "http://$a:$p/health" 2>/dev/null || true)
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.sh, line 89
if [ -n "$tok" ] && [ "$(curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $tok" https://api.github.com/user)" = "200" ]; then
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.sh, line 128
if curl -sf -m 5 "${endpoint%/}/models" >/dev/null 2>&1; then
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/fixtures/verdict-traces.json, line 379
"content": "328:function normalizeResult(\n329- content: string,\n330- model: string,\n331- usage: unknown,\n332- toolCalls: unknown[] | undefined,\n333-): ProviderResult {\n33
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-verdict.test.ts, line 41
{ env: { ...env, REM_TEST_CONSENT: 'off' }, encoding: 'utf8' });
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-verdict.test.ts, line 53
{ env: { ...env, REM_TEST_CONSENT: 'full', REM_TEST_FAIL: '1' }, encoding: 'utf8', stdio: ['ignore', 'pipe', 'pipe'] });
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/login-in-place.test.ts, line 37
writeFileSync(join(config.claude_home, '.credentials.json'), '{"claude":"token"}');
Show more
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-verdict.test.ts, line 61
{ env: { ...env, REM_TEST_CONSENT: 'full' }, encoding: 'utf8' });
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cursor.test.ts, line 168
assert.equal(spawnSync(process.execPath, [COMMAND, 'recall', 'install'], { encoding: 'utf8', env: { ...env, HOME: fresh } }).status, 0);
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall-hook.test.ts, line 110
const cred = join(homedir(), '.claude', '.credentials.json');
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall-hook.test.ts, line 112
copyFileSync(cred, join(iso, '.credentials.json'));
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall-hook.test.ts, line 113
chmodSync(join(iso, '.credentials.json'), 0o600);
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Note
the file cap was reached before every file was read.
OBFUSCATION_FILE_CAP_REACHED
skills/T-delegation-and-work-orders/pl/skills/pl-analyze/scripts/selftest/run-selftest.sh, line 1
#!/usr/bin/env bash
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit a4ea360886ad. requests shell access. The manifest names this permission. install fetches a script from the network. can reach a host that is not written as a fixed address. can reach api.github.com. The description does not name that host. reads a credential or environment file. the file cap was reached before every file was read.
Date and source
Date checked:
github.com
Commit graded: a4ea360886ad796281a9dcc07e44c645397e306b
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.