agy-mcp@0.1.9
CAUTIONPublisher claims: "Skill-first, MCP-second bridge from Claude Code / OpenAI Codex to Google Antigravity CLI (agy)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-26 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; References a credential file in the home directory; 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 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/agymcp
0.2sprocessexited 127: timeout: failed to run command '.venv/bin/agymcp': No such file or directory
0.2sclaimedno tools/list reply (exit 127)
0.2sprocessscript backend runs setup only
Static findings
HIGH
Instructs the agent to modify its persistent memory or instruction filesdocs/installation.md:186 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
References a credential file in the home directorysrc/agy_mcp/adapters/agy.py:886 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03HIGH
Access to sensitive file pathssrc/agy_mcp/supervisor.py:1058 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05CRITICAL
Reads credential paths from the home directorysrc/agy_mcp/safety.py:238 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03HIGH
Auto-update or dynamic fetch configurationsrc/agy_mcp/adapters/agy.py:619 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06HIGH
Instructs the agent to modify its persistent memory or instruction filesdocs/installation.md:185 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Access to sensitive file pathssrc/agy_mcp/bridge.py:177 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
Access to sensitive file pathssrc/agy_mcp/adapters/agy.py:232 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
Access to sensitive file pathssrc/agy_mcp/safety.py:238 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
Credential pass-through configurationsrc/agy_mcp/doctor.py:393 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02HIGH
Refusal suppressionsrc/agy_mcp/_skill_bodies/antigravity/SKILL.md:100 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Access to sensitive file pathssrc/agy_mcp/bridge.py:346 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
Access to sensitive file pathssrc/agy_mcp/adapters/agy.py:886 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
References a credential file in the home directorysrc/agy_mcp/adapters/agy.py:232 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03HIGH
Access to sensitive file pathssrc/agy_mcp/adapters/base.py:117 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Process kill commandsrc/agy_mcp/adapters/base.py:467 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/doctor.py:198 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Process kill commandsrc/agy_mcp/adapters/agy.py:486 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05HIGH
Access to sensitive file pathssrc/agy_mcp/utils.py:457 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Process kill commandsrc/agy_mcp/adapters/base.py:534 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandsrc/agy_mcp/adapters/base.py:376 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/supervisor.py:853 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/adapters/agy.py:215 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/adapters/agy.py:367 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/adapters/gemini.py:89 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/_skill_bodies/claude/scripts/agy_bridge.py:104 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/_skill_bodies/codex/scripts/agy_bridge.py:104 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Process kill commandsrc/agy_mcp/adapters/base.py:550 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/adapters/gemini.py:180 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
File type combined with upload actionsrc/agy_mcp/adapters/base.py:118 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07MEDIUM
Process kill commandsrc/agy_mcp/supervisor.py:22 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandsrc/agy_mcp/adapters/gemini.py:280 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
File permission modification commandsrc/agy_mcp/worktree.py:276 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/worktree.py:88 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/utils.py:396 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
File permission modification commandsrc/agy_mcp/worktree.py:269 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/worktree.py:209 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/worktree.py:107 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
File permission modification commandsrc/agy_mcp/worktree.py:268 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/worktree.py:338 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
File permission modification commandsrc/agy_mcp/worktree.py:267 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05MEDIUM
Python subprocess execution detectedsrc/agy_mcp/worktree.py:373 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
File permission modification commandsrc/agy_mcp/worktree.py:178 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Reads credential paths from the home directory≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim boulea7: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim boulea7