Skills/Glama/agy-bridge

agy-bridge@r1

VERIFIED· install only

Publisher claims: "Zero-Terminal Cross-Agent Context Bus, Lifecycle Hook Sync, and MCP Server connecting Claude Code, Google Antigravity 2.0, OpenAI Codex, and WorkBuddy across shared git worktrees." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher phazww · publishing for 6 daysInstalls 0Last detonated 6d ago
$npx skills add agy-bridge
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

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 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 under the guard. Install scripts ran; no agent task scenario for this bundle. 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 agy-bridge@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-08 and scored it 85/100 (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
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexec /usr/bin/chmod
0.1sprocessexited 1: chmod: cannot access '/tmp/ks-detonate-X8v4js/setup/home/work/acme-api/.claude/skills/project-session-spawner/agy-bridge': No such file or directory
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocesssecond launch, clock +45 days, CI unset
0.2sprocessexec /usr/bin/dirname
0.2sprocessexec /usr/bin/mkdir
0.2sprocessexec /usr/bin/chmod
0.2sprocessexited 1: chmod: cannot access '/tmp/ks-detonate-X8v4js/later/home/work/acme-api/.claude/skills/project-session-spawner/agy-bridge': No such file or directory

Static findings

MEDIUM
File permission modification commandinstall.sh:7 · File permission modification command — agent changes file ownership/permissionschmod +x "$SCRIPT_DIR/agy-bridge"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive file system command detectedDockerfile:3 · Destructive file system command detectedRUN apt-get update && apt-get install -y --no-install-recommends git && rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionCLAUDE.md:11 · File type combined with upload action — agent may exfiltrate local data files- **Claude Code / Desktop** (`~/.claude/settings.json` + `~/.claude.json`): `SessionStart`, `UserPromptSubmit`, `PostToolUse` (`Edit|Write|MultiEdit`), `Stop`, `StopFailure` + MCP server `agy_bridge`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandDockerfile:7 · File permission modification command — agent changes file ownership/permissionsRUN chmod +x /usr/local/bin/agy-bridge && ln -s /usr/local/bin/agy-bridge /usr/local/bin/abFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionAGENTS.md:11 · File type combined with upload action — agent may exfiltrate local data files- **Claude Code / Desktop** (`~/.claude/settings.json` + `~/.claude.json`): `SessionStart`, `UserPromptSubmit`, `PostToolUse` (`Edit|Write|MultiEdit`), `Stop`, `StopFailure` + MCP server `agy_bridge`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedtests/test_agy_bridge.py:48 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(path), "init", "-q", "-b", "main"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agy_bridge.py:55 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(path), "commit", "-q", "-m", "initial commit"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filestests/test_agy_bridge.py:142 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filesubprocess.run(["git", "-C", str(repo), "commit", "-q", "-m", "add CLAUDE.md"], check=True)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/test_agy_bridge.py:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files1. Secret redaction (.env, OpenAI, Anthropic, GitHub, Google, Slack, Bearer tokens)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agy_bridge.py:50 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(path), "config", "user.email", "[email protected]"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_agy_bridge.py:54 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(path), "add", "."], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filestests/test_agy_bridge.py:141 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filesubprocess.run(["git", "-C", str(repo), "add", "CLAUDE.md"], check=True)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_agy_bridge.py:49 · Python subprocess execution detectedsubprocess.run(["git", "-C", str(path), "config", "user.name", "Test User"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈3,229 tok
3 files · 9 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.

agy-bridge@r1 safety verdict: Verified (install only) — KillerSkills