The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx to run the author's own CLI tools (@cobusgreyling/loop, @cobusgreyling/loop-init, @cobusgreyling/loop-audit).
[EXTERNAL_DOWNLOADS]: The skill fetches and executes packages from the npm registry. These packages are owned by the skill's author (cobusgreyling) and are used for their intended purpose of project scaffolding and reporting.
[INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface as it ingests untrusted data from the repository to perform context detection.
Ingestion points: Reads existing project files such as LOOP.md and STATE.md (SKILL.md).
Boundary markers: None present to distinguish between instructions and ingested data.
Capability inventory: Executes shell commands via npx for project initialization, auditing, and status reporting.
Sanitization: No explicit sanitization or validation of the content within LOOP.md or STATE.md is mentioned.

install-loop