wiki-agents-md

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its core functionality of reading and summarizing local repository files.
  • Ingestion points: The skill reads configuration files such as package.json, pyproject.toml, and Cargo.toml, as well as CI/CD workflows in .github/workflows/ and several source code files to identify project patterns.
  • Boundary markers: There are no instructions to use delimiters or ignore embedded instructions within the files being scanned, which could allow malicious content in the repository to influence the generated documentation.
  • Capability inventory: The skill performs file system read operations and writes new AGENTS.md and CLAUDE.md files to the project directory.
  • Sanitization: The instructions do not specify a process for sanitizing or escaping the data extracted from repository files before it is incorporated into the generated instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 06:00 PM