Back to skill

Security audit

letsping

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent human-approval gate, but it asks users to install an unpinned external runtime and gives agents broad autonomous read authority without sensitive-data limits.

Review this before installing. Prefer a pinned, audited package version or commit, run it with a dedicated low-privilege account, protect and scope LETSPING_API_KEY, and add explicit approval rules for reading or transmitting secrets, private logs, credentials, browser/session data, and agent memory.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Error
Location
SKILL.md:15
Finding

Unpinned External Runtime Creates a Mutable Supply-Chain Boundary

Content
View full analysis
Remediation
View remediation
``` 4. Include a lockfile that pins all transitive dependencies and enforce lockfile integrity with `npm ci`. 5. Disable lifecycle scripts during dependency acquisition when they are not required: ```bash npm ci --ignore-scripts ``` 6. Document any lifecycle scripts that are required and review them before enabling execution. 7. Include the runtime source in the auditable artifact or link the documentation to a specific source commit corresponding to the pinned package release. 8. Run the skill with a dedicated low-privilege operating-system account and expose only the environment variables and filesystem paths it requires. ]]>

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:31
Finding

Unrestricted File and Log Reads Are Incorrectly Classified as Safe

Content
View full analysis
$10 - Destructive: Deleting/overwriting files, DB rows, configs - Social: Posting publicly, sending DMs/emails to new contacts, or group chats - Infrastructure: Modifying DNS, env vars, deployments, infra APIs, or permissions When escalating: - Provide tool_name (exact tool, e.g., "system_run") - args_json: Stringified JSON of the original arguments - risk_reason: Clear, concise justification (e.g., "Potential file deletion") ``` The related instructions in `README.md:50-67` state: ```text You have full authority for safe actions: reading files, logs, web searches, data analysis without side effects. You MUST call letsping_ask BEFORE any high-risk action. NEVER execute high-risk actions directly. High-risk includes: - Financial: Spending money, bookings, transactions > $10 - Destructive: Delete/overwrite files, DB rows, configs - Social: Posting, sending DMs/emails to new/public contacts - Infrastructure: Modifying DNS, env vars, deployments, infra APIs Provide: - tool_name: exact tool name - args_json: stringified JSON of arguments - risk_reason: clear justification ``` ### Technical Analysis The recommended agent policy categorically treats reading files and logs as safe. It does not distinguish ordinary project data from sensitive resources such as: - `.env` files and application secrets. - SSH keys and cloud-provider credentials ...[truncated 2405 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

Few-shot examples:

  1. Safe (no call): browser_search(query: "current weather in NYC")
  2. Risky deploy: letsping_ask(tool_name: "vercel_deploy", args_json: "{"project":"my-app","env":"production","force":true}", risk_reason: "Production deployment with force flag")
  3. Risky delete: letsping_ask(tool_name: "system_run", args_json: "{"cmd":"rm -rf /important/folder"}", risk_reason: "Destructive file deletion")
  4. Risky post: letsping_ask(tool_name: "discord_send", args_json: "{"channel":"general","message":"Accidental dump: ls ~"}", risk_reason: "Potential data leak in public channel")
text

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

Few-shot examples:

  1. Safe (no call): browser_search(query: "current weather in NYC")
  2. Risky deploy: letsping_ask(tool_name: "vercel_deploy", args_json: "{"project":"my-app","env":"production","force":true}", risk_reason: "Production deployment with force flag")
  3. Risky delete: letsping_ask(tool_name: "system_run", args_json: "{"cmd":"rm -rf /important/folder"}", risk_reason: "Destructive file deletion")
  4. Risky post: letsping_ask(tool_name: "discord_send", args_json: "{"channel":"general","message":"Accidental dump: ls ~"}", risk_reason: "Potential data leak in public channel")
text

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: letsping
description: Human-in-the-loop approval for high-risk agent actions (sudo protocol). Agent must call letsping_ask before destructive/financial/social/infra changes.
disable-model-invocation: false
metadata:
  openclaw: