agiza_agents

• Verdict: Advisory
• Analyzed: May 10, 2026, 6:49 AM
• Findings: 9
• Version: 1.0.0
• Reason codes:
  suspicious.dangerous_execsuspicious.dynamic_code_executionsuspicious.exposed_secret_literalsuspicious.prompt_injection_instructions
• Engine: v2.4.23

Overview

Detected: suspicious.dangerous_exec, suspicious.dynamic_code_execution, suspicious.exposed_secret_literal (+1 more)

Findings (9)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

ASI04: Agentic Supply Chain Vulnerabilities

NoteMedium Confidence

What this means

Running the command would fetch and install code from outside the registry context.

Why it was flagged

The skill documents a user-run remote install command through npx/GitHub while the registry source is listed as unknown and there is no install spec. This is user-directed and purpose-aligned, but provenance should be checked.

Skill content

npx agent-skills-cli add alirezarezvani/claude-skills/engineering

Recommendation

Only run the npx install command if you trust the package and repository; prefer reviewing or pinning versions before installation.

ASI05: Unexpected Code Execution

NoteHigh Confidence

What this means

The helper scripts can read local project files and produce analysis reports when the user or agent runs them.

Why it was flagged

The sub-skill instructs users to run bundled Python helper scripts against a chosen Terraform directory. This is expected for the stated analyzer/scanner purpose, but it is still local code execution.

Skill content

python3 scripts/tf_module_analyzer.py ./terraform

Recommendation

Run helper scripts only from trusted skill copies and against directories you intend to analyze.

ASI03: Identity and Privilege Abuse

NoteHigh Confidence

What this means

Secrets present in scanned project files could appear in the agent context or generated reports.

Why it was flagged

The Terraform security workflow is designed to inspect code for secrets and IAM issues. This is purpose-aligned, but scanned files may contain credential material.

Skill content

Audit Terraform code for security vulnerabilities, secrets exposure, and IAM misconfigurations

Recommendation

Scan only intended repositories, avoid sharing generated reports publicly, and redact any real secrets found.

ASI01: Agent Goal Hijack

NoteHigh Confidence

What this means

If loaded carelessly, example attack strings may appear in model context, but the artifact labels them as threats to detect.

Why it was flagged

Prompt-injection phrases appear as documented examples in a security-auditor skill, not as instructions to the evaluator or user agent.

Skill content

| **System prompt override** | "Ignore previous instructions", "You are now..." | 🔴 CRITICAL |

Recommendation

Treat these phrases only as examples; load the security-auditor sub-skill only when doing security review work.

Findings (9)

critical

suspicious.dangerous_exec

• Location: skill-security-auditor/scripts/skill_security_auditor.py:161
• Finding: Shell command execution detected (child_process).

critical

suspicious.dynamic_code_execution

• Location: skill-security-auditor/scripts/skill_security_auditor.py:154
• Finding: Dynamic code execution detected.

critical

suspicious.exposed_secret_literal

• Location: api-design-reviewer/references/api_antipatterns.md:441
• Finding: File appears to expose a hardcoded API secret or token.

critical

suspicious.exposed_secret_literal

• Location: api-design-reviewer/references/rest_design_rules.md:350
• Finding: File appears to expose a hardcoded API secret or token.

critical

suspicious.exposed_secret_literal

• Location: helm-chart-builder/references/values-design.md:218
• Finding: File appears to expose a hardcoded API secret or token.

critical

suspicious.exposed_secret_literal

• Location: tech-debt-tracker/assets/sample_codebase/src/user_service.py:14
• Finding: File appears to expose a hardcoded API secret or token.

critical

suspicious.exposed_secret_literal

• Location: terraform-patterns/scripts/tf_security_scanner.py:93
• Finding: File appears to expose a hardcoded API secret or token.

warn

suspicious.prompt_injection_instructions

• Location: skill-security-auditor/references/threat-model.md:75
• Finding: Prompt-injection style instruction pattern detected.

warn

suspicious.prompt_injection_instructions

• Location: skill-security-auditor/SKILL.md:60
• Finding: Prompt-injection style instruction pattern detected.