Skills/npm/semantic-memory

semantic-memory@1.32.0

VERIFIED· install only

Publisher claims: "Unified memory-layer plugin for Claude Code. One MCP server, multiple typed corpora (vault, code, plans, docs, research, project-map), unified cross-corpus knowledge graph, conditional tool registration, in-process drift detection, and human↔code translat" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher theglitchking · publishing for 191 daysInstalls 7,373Last detonated 1 h ago
$claude mcp add semantic-memory -- npx -y @theglitchking/semantic-memory
WatchReport an issue

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-15 and scored it 83/100 (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
0.0sprocessinstall script run in the sandbox
0.1sprocessexited 1: Node.js v22.23.5
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexited 1: Node.js v22.23.5

Static findings

LOW
Instructs the agent to modify its persistent memory or instruction filesdist/core/index.d.ts:841 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file* - If AGENTS.md is absent, write the full contract + an empty Local Notes section.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiondist/core/index.js:215 · File type combined with upload action — agent may exfiltrate local data filesthrow new Error(`evals.json: bad eval ${JSON.stringify(e?.id)}: id (integer), prompt, expected_output and expectations (strings) are required`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/chunk-72VOTNZD.js:155 · npx invocation of non-well-known package — may execute untrusted codecommands: [`semantic-memory eval init ${N}`, `semantic-memory eval ${N}`, `semantic-memory eval ${N} --gaps-out gaps.json`, "/reconcile --gaps gaps.json", "npx hewtd audit"],Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/chunk-H2BES6FU.js:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…[^\s"'\`,;&|()<>\[\]{}]`; var PLACEHOLDER = /^(?:<[^>]*>|\$\{?\w+\}?|(?:process\.env|os\.environ|env)\b.*|\[REDACTED\]|(.)\1{3,}|\*+|x{3,}.*|password|passwd|pass|se…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/chunk-7VBUTARY.js:126 · npx invocation of non-well-known package — may execute untrusted code…= null ? "code-graph export's source_commit is unknown to git; refresh it with `npx hewtd index`" : `code-graph export is ${behind} commits behind HEAD; refresh it with …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/chunk-72VOTNZD.js:220 · npx invocation of non-well-known package — may execute untrusted code…sult says stale: true, the hewtd export is older than the tree; refresh it with npx hewtd index (the healthcheck code-graph-stale finding says the same). A bare filename…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/chunk-72VOTNZD.js:100 · npx invocation of non-well-known package — may execute untrusted code…ory search ${N} --paths "how do we deploy"`, `{"reconcile": {"search_command": "npx semantic-memory search --notes .documentation --paths {query}"}}`, `npx hewtd reconcile --overv…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/chunk-H2BES6FU.js:91 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst env = JSON.parse(readFileSync(join(homedir(), ".claude", "settings.json"), "utf8"))?.env ?? {};Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/cli/index.js:1916 · npx invocation of non-well-known package — may execute untrusted code"Rewrite fragile `npx @latest` entries in .mcp.json to the stable node-against-node_modules form (with backup and validation)"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/cli/index.js:1998 · npx invocation of non-well-known package — may execute untrusted codeconsole.warn(` npx --no @theglitchking/semantic-memory normalize-config`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/chunk-HFMU6L7Z.js:1289 · Process kill command — agent can terminate processeskidnapped kidnapper kidnapping kidney kielbasa kielbasy kill killdeer killjoy kiln kilo kilobyte kilocycleFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/chunk-72VOTNZD.js:188 · npx invocation of non-well-known package — may execute untrusted codecommands: ["semantic-memory gaps --root .", "semantic-memory gaps --root . --json > gaps.json", "npx hewtd reconcile --gaps gaps.json", "semantic-memory usage-set --root ."],Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/cli/index.js:920 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAgents that write "blind" questions have already read \`CLAUDE.md\`, \`AGENTS.md\` and \`.claude/rules/\`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsdist/chunk-MNYGTFQV.js:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesinSettings = Boolean(JSON.parse(readFileSync(claudeSettingsPath(env), "utf8"))?.env?.TYPESAFE_API_KEY);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/cli/index.js:2014 · npx invocation of non-well-known package — may execute untrusted codeif (!opts.json) console.warn(`detected broken npx cache at ${bad} \u2014 clearing and retrying...`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈95 tok
1 file · 81 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 @theglitchking/semantic-memory@1.32.0 as of 49 min ago. This is the package itself, not its dependencies.