T08 · Insecure Dependencies
Warning
- Location
SKILL.md:12- Finding
Unpinned Third-Party Installation Sources Permit Supply-Chain Substitution
- Content
View full analysis
- Remediation
View remediation
Security audit
Travel Planner
Security checks for vulnerabilities and agentic risk
Overview
This is a straightforward travel-planning API wrapper, with expected external sharing of entered waypoints and an API key but no hidden persistence or deceptive behavior found.
Install only from a source and version you trust, preferably a pinned release or reviewed commit. Use this skill only for itineraries you are comfortable sending to Camino's API, and store CAMINO_API_KEY as a normal environment variable or in your agent settings only if you accept that local configuration choice.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)
Agent Config Directory Access
High
- Category
- Agent Snooping
- Confidence
- 90% confidence
- Finding
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
- Content
Add your key to Claude Code:
Add to your
~/.claude/settings.json:json {
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
The skill documents shell-based capabilities (
curl,jq, local scripts) but does not declare an explicit tool scope such aspermissionsorallowed-tools. This creates a mismatch between what the skill can cause an agent to do and what is transparently constrained, increasing the risk of unintended command execution or overbroad tool use.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 91% confidence
- Finding
Using
npx skills add https://github.com/barneyjm/camino-skillsinstalls remote code/content without pinning to a specific commit, tag, or version. If the upstream package or repository changes, users may fetch malicious or unexpected content through a supply-chain compromise.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 91% confidence
- Finding
The skill-specific install command still references a mutable GitHub source via
npx skills add ... --skill camino-travel-plannerwithout pinning. This leaves consumers exposed to repository changes or tampering that could alter the installed skill after publication.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 89% confidence
- Finding
npx clawhub@latest install camino-travel-plannerexplicitly requests the latest version, which is mutable and can introduce unreviewed code at install time. This is a classic supply-chain risk because the fetched package behavior may change between executions.- Content
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
}'
text ### Via curl ```bash curl -X POST -H "X-API-Key: $CAMINO_API_KEY" \
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The script sends user-supplied itinerary data, including waypoint coordinates and trip details, to a third-party API without any explicit disclosure, consent prompt, or redaction step. In a travel-planning context, location and itinerary data can be sensitive and reveal movement patterns, making undisclosed transmission a real privacy issue even though it appears necessary for the feature.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 90% confidence
- Finding
This curl invocation transmits the full JSON input to an external service, which includes user waypoint and travel-planning data. While external transmission is functionally expected for a route optimization skill, it is still a genuine privacy/security concern because the script performs no data minimization, consent check, or destination validation beyond a hardcoded endpoint.
- Content
sh fi # Make API request curl -s -X POST \ -H "X-API-Key: $CAMINO_API_KEY" \ -H "Content-Type: application/json" \ -H "X-Client: claude-code-skill" \
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md -H "Content-Type: application/json" \ -H "X-Client: claude-code-skill" \ -d "$INPUT" \ "https://api.getcamino.ai/journey" | jq .
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
sh -H "Content-Type: application/json" \ -H "X-Client: claude-code-skill" \ -d "$INPUT" \ "https://api.getcamino.ai/journey" | jq .
Static analysis
No suspicious patterns detected.