hactl@r1

VERIFIED· install only

Publisher claims: "Home Assistant admin and debugging for AI agents: health, logs, automation traces, entities and config with capped output. Read-only by default; writes need --allow-writes plus a dry-run and --confirm." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher hemm-ems · publishing for 2 daysInstalls 0Last detonated 2d ago
$npx skills add hactl
WatchReport an issue

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: Verified 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso homeassistant.local — 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 under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$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 hactl@r1 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 81/100 (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 · 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

MEDIUM
File permission modification commandMakefile:204 · File permission modification command — agent changes file ownership/permissions@chmod +x dev/hooks/*Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsinternal/cmd/setup.go:44 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessetupCmd.Flags().BoolVar(&flagSetupForce, "force", false, "overwrite an existing .env without asking (non-interactive mode)")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 pathsinternal/cmd/setup.go:63 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenvPath := filepath.Join(dir, ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Fake instruction boundary tagdocs/llm-tuning.md:57 · Fake instruction boundary tag · informational: not an instruction file…h run was ~40 min on a local Qwen. A smoke test on one prompt (`hactl-llm --td "<prompt>"`) took 2–4 min and was enough to verify a hypothesis before running the full s…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiondev/tuning/run-codex.sh:13 · File type combined with upload action — agent may exfiltrate local data files# <id>.log Tool-call ledger + codex final output (grade.py input)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondev/tuning/run-codex.sh:14 · File type combined with upload action — agent may exfiltrate local data files# <id>.codex.txt full raw codex exec output (tokens-used line at the end)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondev/tuning/run-kilo.sh:13 · File type combined with upload action — agent may exfiltrate local data files# <id>.log Tool-call ledger + kilo final output (grade.py input)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsinternal/cmd/setup.go:72 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Test connectivity — fail fast: do not write .env on error.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 actiondev/tuning/run.sh:11 · File type combined with upload action — agent may exfiltrate local data files# <id>.log raw llm output (tool traces + final answer)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondev/tuning/run-kilo.sh:14 · File type combined with upload action — agent may exfiltrate local data files# <id>.kilo.txt full raw kilo outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsinternal/cmd/setup.go:85 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Write .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 pathsinternal/cmd/setup.go:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesShort: "First-time setup — creates .env in the current directory",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
URL to a private-network addressdev/tuning/qwen35.env:3 · URL to a private-network address — a LAN or development targetexport HACTL_LLM_BASE_URL="http://192.168.42.114:8000/v1"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈3,978 tok
4 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.