ClawHub
Back to skill

Security audit

OpenCal

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its OpenCal meal-tracking purpose, but it gives agents authenticated access to read and change nutrition data with weak destination scoping and limited confirmation guidance.

Review this skill before installing if your OpenCal data is sensitive. Use it only with a trusted OPENCAL_API_KEY environment, do not set OPENCAL_BASE_URL unless you control the endpoint, and require the agent to confirm exact goal changes or deletions before running them.

A.I.G

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

Error
Location
SKILL.md:38
Finding

Bearer Credential and Nutrition Data Exfiltration Through an Unvalidated API Base URL

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

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 49)May include surrounding context.

2. Scale to the actual amount and log:

bash
curl -s -X POST "${OPENCAL_BASE_URL:-https://api.opencal.ai}/api/v1/food/log" \
  -H "Authorization: Bearer $OPENCAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

This PUT request modifies the user's calorie and macro goals on a remote service, which is a state-changing operation with health-relevant consequences if triggered incorrectly. In an agent workflow, ambiguous phrasing or prompt manipulation could cause unauthorized goal changes without the user's informed confirmation.

Content

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

md
-H "Authorization: Bearer $OPENCAL_API_KEY" | jq

# Update (only include fields to change)
curl -s -X PUT "${OPENCAL_BASE_URL:-https://api.opencal.ai}/api/v1/goals" \
  -H "Authorization: Bearer $OPENCAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"calorieGoal": 1800, "proteinGrams": 160}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill includes a destructive API operation that deletes food log entries but does not prominently warn that this action is irreversible or require an explicit user confirmation step. In an agent setting, this increases the chance of accidental or unauthorized data modification if the model misinterprets a request like 'remove that' or acts on ambiguous context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.