Skills/ClawHub/clawdtalk-client

clawdtalk-client@2.0.5

CAUTION· install only

Publisher claims: "ClawdTalk — Voice calls, SMS, and AI Missions for Clawdbot" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher dcasem · publishing for 261 daysInstalls 5,983Last detonated 2 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 8 of 9 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Fake instruction boundary tag; Fake instruction boundary tag. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexec /usr/bin/dirname
0.0sprocessexited 1:
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1: Error: Configuration not found. Run ./setup.sh first.
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1: Error: Config not found. Run ./setup.sh first.
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1: Error: skill-config.json not found. Run setup.sh first.
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: Node.js v22.23.5
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessexec /usr/bin/dirname
0.3sprocessexited 1:
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexec /usr/bin/dirname
0.4sprocessexec /usr/bin/rm
0.4sprocessexited 1:
0.4sprocess8 of 9 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.4sprocesssecond launch, clock +45 days, CI unset
0.4sprocessexec /usr/bin/dirname
0.4sprocessexited 1:

Static findings

CRITICAL
Fake instruction boundary tagSKILL.md:561 · Fake instruction boundary tagpython scripts/telnyx_api.py create-mission <name> <instructions>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:618 · Fake instruction boundary tagpython scripts/telnyx_api.py init <name> <instructions> <request> [steps_json]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:582 · Fake instruction boundary tagpython scripts/telnyx_api.py create-assistant <name> <instructions> <greeting> [options_json]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandupdate.sh:204 · File permission modification command — agent changes file ownership/permissionschmod +x "$SKILL_DIR"/*.sh "$SKILL_DIR/scripts"/*.sh 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/connect.sh:196 · Process kill command — agent can terminate processeskill -9 "$pid" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/connect.sh:143 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Source skill's own .env if it exists (for skill-specific env vars only)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/ws-client.js:745 · File type combined with upload action — agent may exfiltrate local data filesthis.log('ERROR', 'Failed to send deep tool result: ' + err.message);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/ws-client.js:732 · File type combined with upload action — agent may exfiltrate local data filesthis.log('ERROR', 'Failed to send deep tool progress: ' + err.message);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/connect.sh:185 · Process kill command — agent can terminate processesif kill "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/connect.sh:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Env vars: via .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 pathsscripts/call.sh:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"$SKILL_DIR/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/connect.sh:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Reads: skill-config.json, .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/ws-client.js:812 · File type combined with upload action — agent may exfiltrate local data filesthis.log('ERROR', 'Failed to send SMS reply: ' + errText);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/call.sh:45 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"$HOME/.openclaw/.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 pathsscripts/call.sh:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Find .env filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Prompting user to enter sensitive credentialssetup.sh:64 · Prompting user to enter sensitive credentials — social engineeringread -s -p "Enter your API key (or press Enter to skip for now): " api_keyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Access to sensitive file pathsscripts/call.sh:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"$HOME/.clawdbot/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/connect.sh:144 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files[ -f "$SKILL_DIR/.env" ] && . "$SKILL_DIR/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Fake instruction boundary tagSKILL.md:619 · Fake instruction boundary tagpython scripts/telnyx_api.py setup-agent <slug> <name> <instructions> <greeting>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/connect.sh:194 · Process kill command — agent can terminate processes# Force kill if still runningFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/ws-client.js:466 · File type combined with upload action — agent may exfiltrate local data filesthis.log('ERROR', 'sessions_send failed: ' + response.status + ' ' + errText);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 actionscripts/ws-client.js:538 · File type combined with upload action — agent may exfiltrate local data filesthis.log('ERROR', 'Walkie sessions_send failed: ' + response.status + ' ' + errText);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/ws-client.js:971 · Process kill command — agent can terminate processesthis.log('ERROR', ' 1. Find and kill all other ws-client processes:');Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈8,595 tok
1 file · 18 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

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim dcasem: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. 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 ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dcasemPropose a patch to the maintainer