Skills/ClawHub/forge-autonomous-agent-v1

forge-autonomous-agent-v1@1.0.0

CAUTION· install only

Publisher claims: "Advanced autonomous agent framework for research, self-extension, safety, and integration with MCP tools and APIs in professional development environments." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher koppakanagaharsha · publishing for 236 daysInstalls 990Last detonated 1 h ago

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

Is [email protected] 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 2026-11-15 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: Access to sensitive file paths; Prompting user to enter sensitive credentials; Privileged sudo command. 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

HIGH
Access to sensitive file pathsprompts/setup.md:154 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho 'GOOGLE_PASSWORD="[pw]"' >> ~/.forge/.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Prompting user to enter sensitive credentialsprompts/setup.md:305 · Prompting user to enter sensitive credentials — social engineeringPaste the token."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Privileged sudo commandprompts/setup.md:409 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install chromium-browserFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsprompts/setup.md:143 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho 'GEMINI_API_KEY="[KEY]"' >> ~/.forge/.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 pathsprompts/setup.md:68 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesAll credentials go exclusively to ~/.forge/.env.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 pathsprompts/setup.md:100 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files[ -f ~/.forge/.env ] || touch ~/.forge/.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 pathsprompts/system.md:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessource ~/.forge/.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Telegram Bot API URLprompts/setup.md:286 · Telegram Bot API URL — data will be sent to Telegramcurl -s "https://api.telegram.org/bot[TOKEN]/setMyCommands" \Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Pipe-to-shell patternprompts/setup.md:51 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -fsSL https://raw.githubusercontent.com/[USERNAME]/forge/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellprompts/setup.md:51 · Remote installer piped to shellcurl -fsSL https://raw.githubusercontent.com/[USERNAME]/forge/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Telegram Bot API URLprompts/setup.md:272 · Telegram Bot API URL — data will be sent to Telegramcurl -s "https://api.telegram.org/bot[TOKEN]/sendMessage" \Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Prompting user to enter sensitive credentialsprompts/setup.md:181 · Prompting user to enter sensitive credentials — social engineeringPaste the token here.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Direct script execution from GitHub raw URLprompts/setup.md:51 · Direct script execution from GitHub raw URL — unverified code sourcecurl -fsSL https://raw.githubusercontent.com/[USERNAME]/forge/main/install.sh | bashFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈168 tok
1 file · 7 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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim koppakanagaharsha: 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. Prompting user to enter sensitive credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim koppakanagaharshaPropose a patch to the maintainer