scan-automation-project

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a shell command involving find and awk to scan for .test.md files and extract test titles. This operation is localized and serves the specific purpose of generating a test inventory from the project's own documentation.
  • [EXTERNAL_DOWNLOADS]: The skill instructions allow the agent to clone a Git repository if source files are missing from the local environment. This is a standard feature for codebase analysis tools and relies on user-provided locations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it parses content from external files (test titles and filenames) and incorporates them into its output.
  • Ingestion points: Local project files and their metadata, specifically test titles within *.test.md files located in the project or .testeiya/ directory.
  • Boundary markers: The skill does not define specific delimiters or warnings to prevent the AI from interpreting extracted test titles as new instructions.
  • Capability inventory: The skill has the ability to read local files, create a .testeiya/ directory, create symlinks, and modify the project's .gitignore file.
  • Sanitization: No sanitization or validation steps are defined for the data extracted from the codebase before it is presented in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:17 AM
Security Audit — agent-trust-hub — scan-automation-project