readme-generator

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses bash_tool to run a find command to generate a directory tree for project analysis. This is a standard and safe use of the tool for information gathering within the local environment.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes data from untrusted project files to generate a summary.
  • Ingestion points: Project manifests (e.g., package.json, pyproject.toml) and source code entry points (e.g., index.js, main.py) are read to gather context as defined in Step 1 of SKILL.md.
  • Boundary markers: The instructions do not provide delimiters or specific 'ignore' directives to prevent the model from following instructions that might be embedded within the content of these files.
  • Capability inventory: The agent has the capability to read project files, list directories via shell commands, and write the final output to a README.md file.
  • Sanitization: No explicit sanitization or validation of the ingested file content is performed prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 05:38 PM
Security Audit — agent-trust-hub — readme-generator