The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a bundled Python script, scripts/readme_lint.py, to perform structural and content validation on the generated README.md file. The execution is limited to the local environment and targeted at the skill's own diagnostic tool.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes repository files such as package.json, pyproject.toml, Cargo.toml, and existing documentation to gather project information. This ingestion of untrusted external data presents a surface for potential prompt injection if those files contain malicious instructions aimed at the agent.
Ingestion points: Reads project configuration files, dependency manifests, and existing README content as specified in the Workflow section of SKILL.md.
Boundary markers: Absent; the skill does not implement specific delimiters or safety instructions to ignore embedded prompts within the analyzed files.
Capability inventory: Performs subprocess execution of the readme_lint.py script and local file read/write operations (referenced in SKILL.md and implemented in scripts/readme_lint.py).
Sanitization: No specific sanitization or filtering is applied to the data extracted from repository files before it is processed by the agent to generate markdown content.

readme-author