Skills/Glama/github-tools

github-tools@0.11.0

CAUTION· install only

Publisher claims: "Enables coding agents to read and modify GitHub issues, project boards, pull requests, repositories, releases, and Actions through configurable toolsets, with read-only and write-confirmation controls." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher craft-agent · publishing for 8 daysInstalls 0Last detonated 4d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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

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
GH_TOKENSSH_AUTH_SOCKConfiguration, not credentials: EXEC_TEST_LEAK, GH_HOST, GH_PAGER, GH_PROMPT_DISABLED, GH_REPO, GIT_CONFIG_GLOBAL, GIT_CONFIG_NOSYSTEM, GITHUB_ACTIONS, REFS_TEST_UNLISTED, UNLISTED_VARIABLE
Where it talks to
no vendor host named in the code
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. It asks for GH_TOKEN, SSH_AUTH_SOCK and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$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; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 79/100 (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. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocesssecond launch, clock +45 days, CI unset

Static findings

MEDIUM
URL with embedded credentialssrc/core/refs.test.ts:150 · URL with embedded credentials — may be phishing or credential leakingconst repo = repoWithOrigin("https://x-access-token:[email protected]/o")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
URL with embedded credentialssrc/core/refs.test.ts:111 · URL with embedded credentials — may be phishing or credential leaking["https://user:[email protected]/octo/hello.git"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/core/refs.ts:121 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn { ...env, GIT_TERMINAL_PROMPT: "0" }Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathssrc/mcp/server.test.ts:165 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst failure = new Error("ENOENT: no such file '/Users/secret/project/.env'")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialssrc/core/refs.test.ts:138 · URL with embedded credentials — may be phishing or credential leaking["https://x-access-token:[email protected]/o/r?token=ghp_secret#ghp_secret", "gitlab.example"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/entry/settings.ts:148 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst { confirm: _confirm, ...settings } = parseSettings(argv, { ...env, [confirmEnv]: undefined })Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathssrc/mcp/server.test.ts:178 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(logs[0]).toContain("/Users/secret/project/.env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialssrc/core/refs.test.ts:136 · URL with embedded credentials — may be phishing or credential leaking["https://user:[email protected]/o/r", "gitlab.example"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actionscripts/server-json.mjs:37 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Wrote ${output instanceof URL ? fileURLToPath(output) : output} for ${pkg.mcpName} ${pkg.version}.`)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL with embedded credentialssrc/core/refs.test.ts:118 · URL with embedded credentials — may be phishing or credential leaking["https://x-access-token:[email protected]/octo/hello"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Access to sensitive file pathssrc/mcp/server.test.ts:194 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesthrow "/etc/passwd"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathssrc/core/gh.test.ts:189 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(ghEnv()).toMatchObject({ ...env, GH_PROMPT_DISABLED: "1" })Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathssrc/mcp/server.test.ts:202 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(logs[0]).toContain("/etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathssrc/mcp/server.test.ts:201 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(textOf(result)).not.toContain("/etc/passwd")Fix: 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
≈15,490 tok
6 files · 80 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

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim craft-agent: 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. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  4. URL with embedded credentials≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim craft-agentPropose a patch to the maintainer