readme-md-creator
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructions for generating README files and does not contain executable code, network operations, or credential requests. It relies on provided local reference files.\n- [INDIRECT_PROMPT_INJECTION]: The skill workflow involves processing content from untrusted repository files, which represents an indirect prompt injection surface.\n
- Ingestion points: The skill instructs the agent to read existing README.md files, manifests, and project entry points (SKILL.md, Step 1).\n
- Boundary markers: The instructions do not define delimiters to separate content read from files from the system instructions.\n
- Capability inventory: The skill is capable of reading local files and writing Markdown documentation.\n
- Sanitization: The instructions include explicit directives to extract only verified commands and to avoid inventing features, which helps prevent the agent from adopting malicious instructions found in source files.
Audit Metadata