ClawHub
Back to skill

Security audit

播客转文字 Podcast to text (小宇宙 Apple Podcasts)

Security checks for vulnerabilities and agentic risk

Overview

The skill uses the disclosed service, but its default command does not enforce the audio-only processing and pricing it promises.

Have the publisher align the default command with audio-only processing and confirm podcast pricing before use. Set a request or API-key credit cap. Submit only public links: the service says cached digests may be shared with other users in its [privacy policy](https://linkdigest.dev/privacy).

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tainted flow: 'req' from os.environ.get (line 103, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/linkdigest.py (reported line 111)May include surrounding context.

python
if data is not None:
        req.add_header("Content-Type", "application/json")
    try:
        with urllib.request.urlopen(req, timeout=timeout, context=_SSL["context"]) as resp:
            status, headers, raw = resp.status, resp.headers, resp.read()
    except urllib.error.HTTPError as err:
        status, headers, raw = err.code, err.headers, err.read()

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The documented command does not select the audio-only mode even though the skill promises audio-only processing and no base charge. Given the client's full-processing default, following the instructions can request processing outside the user's stated cost and processing expectations, although actual charges depend on server behavior. Broader platform support and keyless summaries are not independently vulnerabilities, and translation is disclosed elsewhere in the document.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The client defaults to full processing rather than enforcing the manifest's audio-only mode.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The parser defaults --depth to full, and the request includes depth only when transcript or script is explicitly selected. Consequently, the normal podcast command does not enforce the promised speech-only, no-base-charge mode and may trigger additional processing or credit consumption depending on API defaults. The optional --max-credits control does not protect ordinary invocations unless explicitly supplied.

Content

No source excerpt is available for this finding.