The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform extensive codebase reconnaissance using shell commands such as find, grep, git, and cat. These are used to map project structure, identify entry points, and analyze data flow.
[EXTERNAL_DOWNLOADS]: In Phase 3, the skill recommends executing npx knip. This command downloads and runs the Knip package from the npm registry to identify unused exports and dependencies in TypeScript projects.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted codebases. This creates a surface for indirect prompt injection where malicious instructions embedded in the audited code could attempt to influence the agent's behavior.
Ingestion points: The skill reads file contents and structures using cat, grep, and find throughout SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within the audited files.
Capability inventory: The skill has the capability to execute shell commands and run tools like npx (as seen in SKILL.md).
Sanitization: No sanitization or validation of the ingested file content is performed before processing.

codebase-analysis