The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and executes an external tool directly from a GitHub repository using npx github:AnEntrypoint/gitoutput. This is a vendor-provided resource used for the skill's primary function of codebase ingestion.
[INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes untrusted data from codebases to generate reports.
Ingestion points: Untrusted codebase files (local or remote Git URLs) are ingested as text chunks using the gitoutput tool (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the ingested codebase chunks (SKILL.md).
Capability inventory: The skill possesses Bash, Read, and Write capabilities; it generates a summary report file and presents it to the user (SKILL.md).
Sanitization: No sanitization or filtering of the ingested content is described before the agent reads the chunks to answer the user's prompt.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a command line involving npx with user-supplied arguments (<target>), which are processed as part of its codebase analysis workflow (SKILL.md).

codebase-text-report