project-readme-writer

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it ingests and processes untrusted data from repository files.
  • Ingestion points: As specified in references/project-detection.md, the skill reads existing README files, CONTRIBUTING files, and various package manifests such as package.json, pyproject.toml, and Cargo.toml to extract metadata and project information.
  • Boundary markers: The instructions do not include boundary markers or specific directives to the agent to ignore instructions found within the files it is analyzing, which is a common vulnerability for indirect prompt injection.
  • Capability inventory: The skill is capable of performing repository-wide file system reads and writing new documentation files (READMEs) across multiple workspaces.
  • Sanitization: There is no evidence of sanitization or validation of the content extracted from the analyzed files before it is used by the agent to generate output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:28 AM
Security Audit — agent-trust-hub — project-readme-writer