The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of shell commands such as find, grep, awk, and wc via reference scripts to analyze the directory structure, count files, and map module dependencies. These commands are executed against the user-provided codebase path to generate technical summaries.- [DATA_EXFILTRATION]: The skill is designed to search for and read project configuration files, including package manifests (package.json, requirements.txt) and environment variable templates (.env.example), to document the project's setup and dependencies.- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection (Category 8). 1. Ingestion points: The skill reads and processes all file names and content within the user-specified codebase directory. 2. Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded commands within the analyzed source code. 3. Capability inventory: The skill has the capability to read local files and execute shell commands. 4. Sanitization: No sanitization or validation is performed on the data ingested from the analyzed codebase before it is used to influence the agent's summary and documentation output.

document-project