ClawHub

skill-c-fetch-minutes

Security checks across malware telemetry and agentic risk

Overview

The skill does what it claims, but it needs Review because it automates sensitive Gitea writes and meeting-data handling with broad repository scope and risky setup defaults.

Install only in a controlled environment with a least-privilege Gitea bot token, HTTPS-only Gitea URL, and a clear list of repositories the bot may modify. Review logs and scan output handling because meeting transcripts and participant emails may be exposed to the runner or orchestration logs. Pin dependencies and avoid sourcing untrusted .env content before production use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill orchestrates shell commands, reads local env files, performs network access, and writes/commits files, yet it declares no explicit permissions. This creates a hidden trust boundary: an agent or reviewer may approve or invoke the skill without realizing it can access credentials, modify repositories, and send external data over the network.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill performs impactful actions—writing meeting artifacts, committing to Gitea, changing workflow status, and triggering outbound organizer email—without an explicit warning or confirmation boundary in the skill description. In an agentic environment, that increases the risk of unintended data modification, accidental disclosure of meeting content, and silent side effects during automated runs.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script aggregates participant email addresses and later emits them in the JSON output, and in some paths also includes full transcript content. That creates a privacy and data-minimization risk: any downstream consumer, log sink, or operator with access to the scan output can obtain personal contact data and potentially sensitive meeting content beyond what is necessary for classification.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The script executes `source "$ENV_FILE"` on a user-editable file, which means any shell code placed in that file will run with the privileges of whoever launches setup. A `.env` file is typically expected to contain passive key/value data, so treating it as executable shell creates a realistic code-execution path if the file is modified maliciously or carelessly.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
python-dotenv>=1.0.0
PyYAML>=6.0
pytz>=2023.3
Confidence
94% confidence
Finding
requests>=2.28.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
python-dotenv>=1.0.0
PyYAML>=6.0
pytz>=2023.3
python-dateutil>=2.8.2
Confidence
94% confidence
Finding
python-dotenv>=1.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
python-dotenv>=1.0.0
PyYAML>=6.0
pytz>=2023.3
python-dateutil>=2.8.2
Confidence
95% confidence
Finding
PyYAML>=6.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
python-dotenv>=1.0.0
PyYAML>=6.0
pytz>=2023.3
python-dateutil>=2.8.2
Confidence
92% confidence
Finding
pytz>=2023.3

Unpinned Dependencies

Low
Category
Supply Chain
Content
python-dotenv>=1.0.0
PyYAML>=6.0
pytz>=2023.3
python-dateutil>=2.8.2
Confidence
92% confidence
Finding
python-dateutil>=2.8.2

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
88% confidence
Finding
requests

Known Vulnerable Dependency: PyYAML — 8 advisory(ies): CVE-2019-20477 (Deserialization of Untrusted Data in PyYAML); CVE-2020-1747 (Improper Input Validation in PyYAML); CVE-2020-14343 (Improper Input Validation in PyYAML) +5 more

Critical
Category
Supply Chain
Confidence
90% confidence
Finding
PyYAML

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal