Back to skill

Security audit

linkdigest-viral-breakdown

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently analyzes user-supplied social-media links through LinkDigest, with disclosed costs and data sharing.

Submit only public links and remove private details from share text. LinkDigest processes content through third parties and may share cached results for the same link. Protect your API key and use --max-credits to limit spending. Without a key, expect a summary rather than a breakdown. Prefer the bundled client or direct HTTP; pin a reviewed version if using the optional npm bridge.

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
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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Tainted flow: 'req' from os.environ.get (line 102, 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 110)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
94% confidence
Finding

The API integration is consistent with the declared service, but the implementation exposes additional translation functionality and an explicitly supported no-key access path. These are concrete differences from the description. The code only requests breakdowns when --breakdown is supplied and otherwise functions as a general content reader. It does not itself verify quotations, remove mismatched quotations, or report deletion counts; those guarantees cannot be confirmed because any such processing would have to occur in the unseen service or another skill component. No unrelated file modification, shell execution, or credential collection is evident.

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.

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 · SKILL.md (reported line 84)May include surrounding context.

直接调 HTTP(没有 Python 时)

bash
curl -sS -X POST https://linkdigest.dev/api/v1/digest \
  -H "Authorization: Bearer $LINKDIGEST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://v.douyin.com/<短链>/", "format": "json", "breakdown": true}'

MCP server referenced without pinned version: 'npx mcp-remote'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The optional npx mcp-remote command can download and execute an unpinned npm package with the user's local privileges. A compromised future release or dependency could access local data and the API credential passed to the process; this is a supply-chain exposure, not evidence that the current package is malicious.

Content

No source excerpt is available for this finding.

Missing API credentials trigger a keyless summary request instead of enforcing the manifest's API-key requirement and breakdown behavior.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest states that LINKDIGEST_API_KEY is required and describes a viral-content breakdown. However, L306–L307 automatically invoke free_look when the key is absent, and L142 submits the supplied content while stripping the breakdown option and all other fields except url and depth. This path produces only a summary rather than the advertised breakdown, and successful responses can still exit successfully through L152–L153.

Content

No source excerpt is available for this finding.