ClawHub
Back to skill

Security audit

Step Asr

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward remote transcription skill that sends user-selected audio to StepFun's ASR API using the user's StepFun API key.

Install only if you are comfortable sending selected audio files and any prompt text to StepFun for transcription, and avoid using it for sensitive recordings unless that fits your privacy and data-handling requirements.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tainted flow: 'req' from os.environ.get (line 95, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
)

    try:
        resp = urllib.request.urlopen(req)
    except urllib.error.HTTPError as e:
        err_body = e.read().decode("utf-8", errors="replace")
        print(f"HTTP {e.code}: {err_body}", file=sys.stderr)
Confidence
90% confidence
Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill performs network access, reads an API key from the environment, and can write output files, but it does not declare any explicit tool scope or permissions. This weakens least-privilege controls and transparency for users, increasing the chance that the skill is run with broader capabilities than expected.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill sends user-provided audio to an external ASR provider, but the description and usage text do not clearly warn about this data transfer. Audio may contain sensitive speech, personal information, or confidential business content, so failing to disclose third-party transmission creates a privacy and consent risk.

External Transmission

Medium
Category
Data Exfiltration
Content
import urllib.request
import urllib.error

API_URL = "https://api.stepfun.com/v1/audio/asr/sse"

FORMAT_MAP = {
    ".pcm": ("pcm", "pcm_s16le"),
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script transmits the full audio content to an external ASR service without any explicit runtime warning, confirmation, or privacy notice. In a transcription tool, network transmission is expected, but audio may contain sensitive personal, financial, medical, or corporate information, so silent exfiltration to a third party creates a real privacy and data-governance risk.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The CLI sets `--language` to `zh` by default, which imposes a specific language/locale choice unless the user overrides it. This is a natural-language policy concern because the tool does not first ask the user to choose a language or make the default locale-neutral.

Static analysis

No suspicious patterns detected.