ClawHub
Back to skill

Security audit

Transcribe audio via Groq API (~10x cheaper than OpenAI API)

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims by sending selected audio to Groq for transcription, but its shell script has a real argument-handling flaw that can unintentionally upload other local files.

Review this before installing or using it with automated inputs. It is appropriate for sending chosen audio files to Groq, but avoid passing untrusted values into --prompt, --model, or --language until the script uses literal form fields such as --form-string for non-file parameters. Do not use it for confidential recordings unless you are comfortable sending them to Groq's API.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/transcribe.sh:75
Finding

Arbitrary Local File Disclosure Through Unsafe curl Multipart Form Values

Content
View full analysis
Remediation
View remediation
"$out" ``` Using an argument array also prevents unintended word splitting and preserves prompts containing spaces or shell metacharacters. As defense in depth: 1. Validate `model` against an explicit allowlist of supported model identifiers. 2. Validate `language` against the expected language-code format. 3. Add regression tests using values such as `@/etc/passwd` and verify that no local file content is included in the request. 4. Run the Skill with the minimum filesystem permissions required for its intended operation. ]]>

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill invokes shell-based functionality (curl via a script) but does not declare any tool scope such as permissions or allowed-tools. That weakens least-privilege controls and can cause the agent or reviewer to underestimate the skill's execution capabilities, which is especially relevant because the skill handles user-supplied file paths and network access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation does not clearly warn users that provided audio is transmitted to Groq's remote API for transcription. This creates a privacy and data-handling risk because users may supply sensitive recordings under the assumption processing is local, leading to unintended disclosure of confidential or regulated content to a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/transcribe.sh (reported line 75)May include surrounding context.

sh
mkdir -p "$(dirname "$out")"

curl -sS https://api.groq.com/openai/v1/audio/transcriptions \
  -H "Authorization: Bearer $GROQ_API_KEY" \
  -H "Accept: application/json" \
  -F "file=@${in}" \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This shell script uploads the provided audio file to a remote service using curl, which transmits potentially sensitive user data off-system. Although network transmission is central to transcription, the file itself provides no explicit warning, confirmation, or descriptive comment/log indicating that the audio will be sent to Groq's external API.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.