Skills/Glama/tg-archive

tg-archive@0.1.0

CAUTION· install only

Publisher claims: "Enables Claude to search an archived collection of public Telegram channel posts by keywords and semantic meaning, retrieve individual posts, view recent posts, list topics, and get archive statistics through MCP tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher myshli · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

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
MCP_TOKENOPENAI_API_KEYConfiguration, not credentials: ARCHIVE_DB, DIGEST_CLUSTER_EFFORT, DIGEST_CLUSTER_MODEL, DIGEST_EPOCH, DIGEST_FLEX, DIGEST_THIN_CHARS, DIGEST_THIN_MODEL, DIGEST_WRITE_EFFORT, DIGEST_WRITE_MODEL, DOMAIN, EMBED_DIM, EMBED_MODEL, MCP_HOST, MCP_PORT, MEDIA_DIR, MEDIA_MAX_MB, SITE_DIR, SITE_URL, TAG_EFFORT, TAG_MODEL, TAG_WORKERS, TG_API_HASH, TG_API_ID, TG_SESSION
Where it talks to
no vendor host named in the codeAlso astral.sh, t.me — 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
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 astral.sh, t.me as well as its own vendor. The guard injects MCP_TOKEN, OPENAI_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 2026-11-12 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; 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 · 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

HIGH
Access to sensitive file pathsmcp_server.py:23 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(ROOT / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commanddeploy/go-public.sh:39 · File permission modification command — agent changes file ownership/permissionschown tgarchive:tgarchive-db /var/lib/tg-archive/archive.dbFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsdb.py:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files_ENV = Path(__file__).parent / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/env.sh:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files[ -f .env ] && grep -E "^$1=" .env | tail -n 1 | cut -d= -f2- | sed -E 's/^"(.*)"$/\1/' || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsmedia.py:28 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(ROOT / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/push.sh:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesrsync -az .env tg.session "$HOST:$DIR/"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commanddeploy/go-public.sh:52 · File permission modification command — agent changes file ownership/permissionschmod 600 /etc/tg-archive-mcp.envFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsmcp_server.py:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif os.access(ROOT / ".env", os.R_OK): # see db.pyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/env.sh:2 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Only these two keys are read; the secrets in .env are not loaded into the shell.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commanddeploy/go-public.sh:40 · File permission modification command — agent changes file ownership/permissionschmod 660 /var/lib/tg-archive/archive.dbFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsenrich.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(ROOT / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/go-public.sh:88 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "tgmcp reads .env? $(runuser -u tgmcp -- cat /opt/tg-ml-archive/.env >/dev/null 2>&1 && echo YES-BAD || echo no)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/push.sh:4 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# deploy/push.sh --with-data # first time: also .env, tg.session and archive.dbFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/go-public.sh:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesgrep "^EMBED_DIM=" /opt/tg-ml-archive/.env || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdigest.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(ROOT / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsingest.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(ROOT / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/go-public.sh:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# the OpenAI key copied from the ingest .env; root-only, never printed)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/env.sh:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "DEPLOY_HOST is not set: add DEPLOY_HOST=user@server to .env (see .env.example)" >&2Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/env.sh:1 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Sourced by the deploy scripts. Reads DEPLOY_HOST and DOMAIN from the shell, or else from .env.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/push.sh:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesssh "$HOST" "chmod 600 $DIR/.env $DIR/tg.session && chown $APP_USER:tgarchive-db $DATA/archive.db && chmod 660 $DATA/archive.db"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commanddeploy/push.sh:31 · File permission modification command — agent changes file ownership/permissionsssh "$HOST" "chmod 600 $DIR/.env $DIR/tg.session && chown $APP_USER:tgarchive-db $DATA/archive.db && chmod 660 $DATA/archive.db"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsdeploy/push.sh:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# .env and tg.session stay 600.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/push.sh:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesMCP_USER=tgmcp # runs the public MCP server; cannot read tg.session or .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/go-public.sh:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif [ -z "$DOMAIN" ]; then echo "DOMAIN is not set: add it to .env" >&2; exit 1; fiFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy/go-public.sh:48 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesgrep "^OPENAI_API_KEY=" /opt/tg-ml-archive/.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)mcp_server.py:4 · MCP server using network transport (SSE/HTTP) — data sent over networkuv run mcp_server.py --http # streamable HTTP on 127.0.0.1:8765/mcp, needs MCP_TOKENFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedmedia.py:76 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commanddeploy/push.sh:36 · File permission modification command — agent changes file ownership/permissionsssh "$HOST" "chown -R $APP_USER:$APP_USER $DIR && chmod 755 $DIRFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedmedia.py:54 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmedia.py:71 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmedia.py:81 · Python subprocess execution detectedsubprocess.run([FFMPEG, "-y", "-v", "error", "-i", str(dst), "-frames:v", "1", "-q:v", "4", str(poster)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈38 tok
1 file · 19 in bundle

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

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim myshli: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  4. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
  5. 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 Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim myshliPropose a patch to the maintainer