ClawHub
Back to skill

Security audit

飞书发文件(免费)

Security checks across malware telemetry and agentic risk

Overview

This skill matches its Feishu file-sending purpose, but it handles local files and app secrets with broad raw commands and limited user-control guidance.

Review before installing. Use this only when you intend the agent to send a specific non-sensitive file to a specific Feishu recipient, and avoid letting it print or scrape app secrets from local config files. Prefer providing credentials through a managed secret store and confirm the file path and open_id before each send.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
87% confidence
Finding
The skill explicitly instructs operators to read `appId` and `appSecret` from a local config file using shell commands, which encourages direct access to broader local secrets during routine use. In an agent context with `read`, `grep`, and `exec` capabilities, this expands the skill from file sending into credential discovery and increases the risk of unintended secret exposure in logs, prompts, or downstream command output.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The description is broad and open-ended, framing the skill as generally applicable for Feishu file-sending scenarios without strict trigger constraints, approval requirements, or destination validation. In an agent environment, vague invocation boundaries make it easier to use the skill for unreviewed file exfiltration or accidental transmission of sensitive local files.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill describes command execution and external file transmission as core behavior, but it does not prominently warn users that local files may be uploaded to an external service and sent to another party. This omission is risky because users may invoke the skill without realizing it can cause outbound data transfer from the local environment.

External Transmission

Medium
Category
Data Exfiltration
Content
-d '{"app_id":"<APP_ID>","app_secret":"<APP_SECRET>"}' \
  | python3 -c "import json,sys; print(json.load(sys.stdin)['tenant_access_token'])")
# ...
FILE_KEY=$(curl -s -X POST "https://open.feishu.cn/open-apis/im/v1/files" \
  -H "Authorization: Bearer $TOKEN" \
  -F "file_type=stream" \
  -F "file_name=<文件名>" \
Confidence
93% confidence
Finding
This is an actual external transmission primitive: the documented command uploads a local file to Feishu using `curl` and then sends it onward via message API. In context, the capability is aligned with the skill's stated purpose, but it remains security-sensitive because any misuse or prompt manipulation could exfiltrate arbitrary local files to an external service.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.