The Agent Skills Directory

[PROMPT_INJECTION]: No instructions attempting to override agent behavior or bypass safety guidelines were detected in the skill markdown or metadata.
[DATA_EXFILTRATION]: No network operations or access to sensitive credential files (such as .ssh or .aws directories) were found. The skill interaction is limited to standard project configuration files.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote script downloads or execution from external sources.
[COMMAND_EXECUTION]: No shell commands or subprocess calls are present. The skill uses platform-provided tools for file operations.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or tokens were found in the provided files.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes project files that could contain malicious instructions.
Ingestion points: Uses Glob and Read to analyze project files like package.json, pyproject.toml, and source code in SKILL.md.
Boundary markers: Absent. The skill does not specify delimiters or instructions to disregard potential commands within analyzed files.
Capability inventory: Includes the Write tool to generate or update the README.md file.
Sanitization: Absent. The skill does not specify validation or escaping for the content ingested from the codebase.

readme-generator