Back to skill

Security audit

Quran Api

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Quran lookup helper that queries a disclosed public API and prints Arabic results.

Install only if you are comfortable with Quran lookup requests being sent to api.alquran.cloud. Expect Arabic output, and note that the advertised search command is currently not implemented.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · scripts/quran_search.sh (reported line 22)May include surrounding context.

sh
case "$ACTION" in
  "surah_by_number")
    curl -s "${BASE_URL}/surah/${PARAM}/ar" | python3 -c "
import sys, json
data = json.loads(sys.stdin.read())
if data['code'] == 200:

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · scripts/quran_search.sh (reported line 39)May include surrounding context.

sh
"
    ;;
  "ayah")
    curl -s "${BASE_URL}/ayah/${PARAM}/ar" | python3 -c "
import sys, json
data = json.loads(sys.stdin.read())
if data['code'] == 200:

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · scripts/quran_search.sh (reported line 54)May include surrounding context.

sh
"
    ;;
  "page")
    curl -s "${BASE_URL}/page/${PARAM}/ar" | python3 -c "
import sys, json
data = json.loads(sys.stdin.read())
if data['code'] == 200:

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · scripts/quran_search.sh (reported line 68)May include surrounding context.

sh
"
    ;;
  "juz")
    curl -s "${BASE_URL}/juz/${PARAM}/ar" | python3 -c "
import sys, json
data = json.loads(sys.stdin.read())
if data['code'] == 200:

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 36)May include surrounding context.

md
## API

Base URL: `https://api.alquran.cloud/v1/`

## التجربة

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file header documents bash quran_search.sh search "keyword" - Search all surahs, and the usage string also lists search as a supported action. However, the case statement only implements surah_by_number, ayah, page, and juz; search falls into the default usage branch instead of performing a search. This is an active contradiction between the documented capability and actual behavior.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
79% confidence
Finding

The script sends user input to an external service over the network, which creates a real data-exposure boundary. In this skill's context the transmitted data appears limited to Quran lookup parameters, so the risk is low, but it is still a genuine external transmission that may be unacceptable in privacy-sensitive or offline-only environments.

Content

Scanner excerpt · scripts/quran_search.sh (reported line 18)May include surrounding context.

sh
ACTION="$1"
PARAM="$2"

BASE_URL="https://api.alquran.cloud/v1"

case "$ACTION" in
  "surah_by_number")

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

All API calls hardcode the '/ar' endpoint and the printed labels are in Arabic, which enforces a specific language/locale without user opt-in. The policy requires either offering a language choice or clearly documenting and justifying the locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language content throughout the skill file is exclusively in Arabic, which can functionally force a specific language on users without any opt-in or stated justification. Under the policy rule, locale or language constraints should either be optional for the user or clearly documented as intentional and necessary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This shell script makes outbound HTTP requests to a third-party Quran API using curl, which transmits the user-supplied query parameter off-host. Although the file header shows usage examples, there is no explicit warning or disclosure near execution that user input will be sent to an external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The ayah, page, and juz branches likewise issue outbound requests to the same external API, but the script does not provide an explicit warning that these operations contact a remote service. This matters because the safety criterion calls for some form of user disclosure for network transmission of user or system data.

Content

No source excerpt is available for this finding.