Skills/Glama/krusch-git

krusch-git@1.2.4

VERIFIED

Publisher claims: "Enables AI coding agents to semantically search an indexed codebase and traverse AST symbol, call-graph, and Markdown section dependencies persisted in PostgreSQL with pgvector. Applies temporal recency decay and hybrid lexical/vector ranking so agents can retrieve and hydrate the most relevant code across entire repositories." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher kruschdev · publishing for 0 daysInstalls 0Last detonated 1 h ago
$npx skills add krusch-git
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
API_KEYDATABASE_URLHYDRADB_API_KEYKRUSCH_GIT_API_KEYPG_CONNECTION_STRINGREQUIRE_API_KEY_LOCALConfiguration, not credentials: CORS_ORIGIN, CORS_ORIGINS, DEBUG_BACKFILL, EMBED_CODE_SYMBOLS, HYDRADB_BASE_URL, HYDRADB_COLLECTION, HYDRADB_DATABASE, HYDRADB_GIT_DATABASE, HYDRADB_GIT_SYNC, KRUSCH_EPHEMERAL, KRUSCH_GIT_MOCK_DB, KRUSCH_OLLAMA_HOST, KRUSCHDEV_OLLAMA_HOST, KRUSCHDEV_TAG_HOST, KRUSCHSERV_OLLAMA_HOST, KRUSCHSERV_TAG_HOST, MOCK_EMBEDDINGS, MONOREPO_ROOT, NODE_TEST_CONTEXT, OLLAMA_CONCURRENCY, OLLAMA_EMBED_HOST, OLLAMA_MAX_CONCURRENCY, OLLAMA_NODES, OLLAMA_SUMMARY_HOST, OLLAMA_SUMMARY_MODEL, OLLAMA_URL, REEMBED_STALE_MODEL, SKIP_LLM_SUMMARY, SYMBOL_STORAGE_MODE, TAG_CONCURRENCY, TAG_MODEL, TAG_OLLAMA_HOST
Where it talks to
no vendor host named in the codeAlso vite.dev, hydradb.com, huggingface.co — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names vite.dev, hydradb.com, huggingface.co as well as its own vendor. The guard injects API_KEY, DATABASE_URL, HYDRADB_API_KEY, KRUSCH_GIT_API_KEY, PG_CONNECTION_STRING, REQUIRE_API_KEY_LOCAL 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 (2 scenarios) on 2026-11-21 and scored it 84/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 26 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.5sprocessdependency install exit 0
26sclaimed7 tools: krusch_git_list_repos, krusch_git_read_tree, krusch_git_read_blob, krusch_git_semantic_search, krusch_git_search_symbols, krusch_git_file_symbols, krusch_git_dependency_graph
26stools17706961129ddf80
26stools9615508b203b32cc
26stools8e5eab35786125ef
26stools518233d8963008a6
26stools7303c960986dfe69
26stoolsa5588dbc5fd5c75d
26stools44f2dc19b5e9464c
26sprocessscript backend runs setup only
26sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsscripts/sync_to_pg.js:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…build', '__pycache__', '.ruff_cache', '.mypy_cache', 'data', 'tmp', '.gemini', '.credentials', '.secrets', '.venv', 'venv', 'bench_venv', 'mcp_env', '.vscode', 'nodes', 'sa…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 pathslib/embedding.js:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'.toml', '.env', '.dockerfile', '.graphql', '.vue', '.svelte'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 pathsconfig.js:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Load .env variables into process.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 pathsconfig.js:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv.config({ path: join(__dirname, '.env'), quiet: true });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondb/migrate.js:11 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Connecting to PostgreSQL database...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathsdocker-compose.yml:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈652 tok
2 files · 75 in bundle
Tool list per prompt
≈987 tok
7 tools · 141 per tool
Handshake
3771 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 115

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

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.