Back to skill

Security audit

life-coupon-expert

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rated this skill suspicious because it reports exposed credentials, unencrypted product searches, and weak disclosure and intent checks; analysis was also incomplete.

Consider the suspicious verdict before installing. The scanners report that credentials may be distributed, search terms can leave the assistant environment without clear disclosure and travel over unencrypted HTTP, and searches may start without clear coupon-seeking intent. Skillspector analyzed 7 of 8 components; one referenced image was not fully inspectable, so the evidence is incomplete.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
skills/life-deal-finder/SKILL.md
Finding

Product searches transmit credentials and consume results over unauthenticated HTTP

Content
View full analysis

Impact

Search terms are exposed to network observers. Response manipulation can replace selected products or falsify coupon information before downstream link generation. HTTPS on the subsequent request does not authenticate the earlier search results.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
- `avatars/expert.png`

The “zero-configuration” packaging requirement directs disclosure of real local credentials in the distributed skill documentation.

High
Category
Data Exfiltration
Confidence
99% confidence
Finding

The packaging gate requires real local credentials to appear in the distributed skill documentation, and the archive includes that documentation. Recipients can extract and reuse the API key outside the intended agent, potentially exhausting quotas or exercising whatever account permissions the service actually grants; omitting sensitive endpoint examples does not enforce access control.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 17)May include surrounding context.

md
## 架构

- `agents/life-coupon-expert.md` — 专家人设
- `skills/life-deal-finder/SKILL.md` — 九个实测接口速查 + 工作流程 + 输出规范 + 合规红线

依赖:无(接口凭据已内置,即装即用)。

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
- `agents/life-coupon-expert.md`
- `avatars/expert.png`
- `skills/life-deal-finder/README_____.md`
- `skills/life-deal-finder/SKILL.md`

## Notes

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

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 keyword-search workflow lacks disclosure that user-provided shopping queries are sent to external coupon services.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow directs immediate keyword searches through an external coupon API without explaining that user-derived shopping terms leave the assistant environment. External searching is relevant to the requested service, but sensitive purchase interests can still be disclosed without the user understanding the recipient or data flow.

Content

No source excerpt is available for this finding.

Everyday category words trigger coupon-link generation without requiring deal-seeking intent.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The trigger rules explicitly treat ordinary category words, including medicine and travel, as sufficient reason to generate coupon links without checking for shopping or deal-seeking intent. Although surrounding rules discourage unrelated recommendations, this broad activation rule can still cause unsolicited affiliate activity and external requests during informational or sensitive conversations.

Content

No source excerpt is available for this finding.

The product-search workflow sends user-derived search terms to a third party without a privacy warning.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The search request places user-derived keywords in a third-party URL without a privacy disclosure, exposing shopping interests to the provider and potentially its request logs. The documented search endpoint also uses plaintext HTTP, allowing network intermediaries to observe those keywords and the API key; being read-only does not protect confidentiality.

Content

No source excerpt is available for this finding.