iac-security-scan-skills

Warn

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to download security scanning components from an unverified third-party GitHub repository (github.com/senaykt/iac-security-scan-skills.git) that is not associated with a verified vendor or organization.
  • [REMOTE_CODE_EXECUTION]: The scanner relies on external orchestration files (AGENTS.md, CLAUDE.md, and various skill directories) that are loaded into the agent's environment to define execution logic and behavior. Loading unverified external scripts and configurations poses a risk of unauthorized command execution.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and analyzes untrusted Infrastructure-as-Code (IaC) configuration files which could contain malicious instructions.
  • Ingestion points: Reads local project files including .tf, .hcl, .yaml, .yml, and .json during analysis and domain scanning.
  • Boundary markers: There are no instructions in the provided documentation indicating the use of delimiters or 'ignore' commands to isolate untrusted data from the agent's instructions.
  • Capability inventory: The skill can execute subprocesses for scanning, perform network-related analysis (simulated), and write multi-format reports (HTML, CSV) to the local filesystem.
  • Sanitization: No sanitization or validation of the ingested IaC content is mentioned, allowing arbitrary file content to enter the agent context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 12, 2026, 08:51 PM
Security Audit — agent-trust-hub — iac-security-scan-skills