The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions require the agent to execute various shell commands including npm audit, pip list --outdated, cargo audit, and govulncheck. These are standard tools for identifying dependency issues in software projects.
[EXTERNAL_DOWNLOADS]: The skill references the installation of several external auditing utilities from well-known registries, such as pip-audit, safety, pip-licenses, and go-licenses. It also provides a git clone command to install the skill itself from the author's repository.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and parsing project manifest files, which introduces a surface for indirect prompt injection.
Ingestion points: The skill reads package.json, package-lock.json, pyproject.toml, poetry.lock, Cargo.toml, Cargo.lock, go.mod, and requirements.txt from repositories specified by the user.
Boundary markers: The instructions do not define specific delimiters or security headers to prevent the agent from following instructions embedded within these manifest files.
Capability inventory: The skill utilizes shell command execution via package managers and security tools, which could be leveraged if the agent is manipulated by malicious file content.
Sanitization: No explicit sanitization, schema validation, or content filtering is described for the data ingested from the project manifests.

dep-audit