Back to skill

Security audit

termux-compat-runner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed dry-run command classifier for Termux use and does not execute commands itself.

This skill is reasonable to install if you want advisory Termux command validation. Treat its script as a simple regex-based classifier, not a complete security sandbox or full compatibility checker, and continue to review any command before running it yourself.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill claims broad Termux compatibility checks, platform detection, and tool availability validation, but the described behavior appears to be a much narrower command classifier/allowlist model. This mismatch is dangerous because users may rely on safety guarantees that are not actually enforced, leading to unsafe command recommendations or false trust in validation results.

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% 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 · README.md (reported line 32)May include surrounding context.

md
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% 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 160)May include surrounding context.

md
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% 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 · scripts/run_safe.sh (reported line 20)May include surrounding context.

sh
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% 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 · README.md (reported line 32)May include surrounding context.

md
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% 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 160)May include surrounding context.

md
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% 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 · scripts/run_safe.sh (reported line 20)May include surrounding context.

sh
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% 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 · README.md (reported line 32)May include surrounding context.

md
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% 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 160)May include surrounding context.

md
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% 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 · scripts/run_safe.sh (reported line 20)May include surrounding context.

sh
# Usage:
#   bash scripts/run_safe.sh "ss -tulpen" --timeout 60
#   bash scripts/run_safe.sh "pkg update" --timeout 60
#   bash scripts/run_safe.sh "rm -rf /tmp/old"   # DENIED
set -uo pipefail

cmd="${1:-}"

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
79% confidence
Finding

The skill describes shell-related validation behavior but does not declare a formal tool scope such as explicit permissions or allowed-tools. That gap can cause downstream systems or reviewers to misunderstand what shell capabilities the skill expects, increasing the chance of unintended shell access or unsafe integration behavior.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
- `systemctl` / systemd commands
- Paths `/usr/local/...`, `/etc/systemd`
- Desktop-only binaries without fallback
- glibc-only commands without verification

**USE Termux alternatives:**
- `pkg` for package management