The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs extensive shell command execution to detect project environment manifests and run audit/update tools for Go, Node.js, Python, Rust, and Ruby. It also executes project-specific test suites to verify updates.
[EXTERNAL_DOWNLOADS]: The skill initiates downloads and installations of auditing tools (such as pip-audit and cargo-audit) and project dependencies from well-known package registries including npm, PyPI, Crates.io, and RubyGems.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by reading and processing data from untrusted external sources.
Ingestion points: Reads project manifest files (e.g., package.json, requirements.txt), lock files, LICENSE files, and external documentation such as changelogs and migration guides.
Boundary markers: Absent; external content is interpolated directly into the agent's reasoning process without explicit delimiters.
Capability inventory: Full file system access within the project directory, execution of arbitrary commands (tests and tools), and network access via package managers.
Sanitization: No explicit sanitization or validation of the content fetched from external sources is specified before it is processed by the agent.
[DYNAMIC_EXECUTION]: The skill dynamically constructs and executes shell commands based on the detected project ecosystem and the requested update scope.

deps