ClawHub
Back to skill

Security audit

IMC Publish

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it helps publish or schedule social posts through an InstallMyClaw workspace, with disclosed credential use and confirmation instructions.

Install only if you intend to let your agent help publish to your connected social channels. Keep IMC_PUBLISH_API_KEY in your shell or secrets manager, do not paste it into chat, leave IMC_PUBLISH_BASE unset unless you trust the endpoint, and require a clear preview plus your explicit yes before any confirm or post command is run.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Tainted flow: 'request' from os.environ.get (line 62, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
},
    )
    try:
        with urllib.request.urlopen(request, timeout=180) as response:
            return json.loads(response.read().decode("utf-8"))
    except urllib.error.HTTPError as exc:
        raw = exc.read().decode("utf-8", "replace")
Confidence
91% confidence
Finding
with urllib.request.urlopen(request, timeout=180) as response:

Vague Triggers

Medium
Confidence
80% confidence
Finding
The README states that the skill triggers automatically on publish-related requests, but does not define a narrow activation scope. In an agent environment, broad trigger language can cause the skill to activate on common user prompts and initiate social publishing workflows unexpectedly, increasing the chance of accidental posting or exposure of sensitive draft content.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger list is broad enough to activate on generic phrases like "publish," "post to," and platform names, which can cause the skill to be invoked when the user did not specifically intend to use this publishing capability. In a skill that can ultimately publish to external social accounts, unintended invocation increases the chance of drafting or guiding toward high-impact actions on the wrong tool or workflow.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The post command performs immediate publishing without any interactive confirmation, dry-run, or additional safeguard. In an agent or automation context, this increases the chance of accidental irreversible posting to connected social accounts, especially because the same tool also supports a safer draft/confirm workflow.

Session Persistence

Medium
Category
Rogue Agent
Content
set -euo pipefail
SRC="$(cd "$(dirname "$0")" && pwd)"
DEST="$HOME/.claude/skills/imc-publish"
mkdir -p "$HOME/.claude/skills"
rm -rf "$DEST"
cp -r "$SRC" "$DEST"
rm -f "$DEST/install.sh" "$DEST/uninstall.sh"
Confidence
82% confidence
Finding
mkdir -p "$HOME/.claude/skills" rm -rf "$DEST" cp -r "$SRC" "$DEST" rm -f "$DEST/install.sh" "$DEST/uninstall.sh" echo "Installed to $DEST" echo echo "Next: set your workspace publishing key (ask your

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.