The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to run local scripts (quick_validate.py, eval_workspace.py, token_budget.py, package_skill.py) and the skills-ref CLI tool to automate a shipping pipeline.
[PROMPT_INJECTION]: The skill processes external skill files, creating an attack surface for indirect prompt injection where malicious instructions in the target skill could influence the agent's behavior.
Ingestion points: Untrusted data enters the context when the agent reads files from the path specified in $ARGUMENTS (SKILL.md).
Boundary markers: No specific delimiters or 'ignore' instructions are used to isolate the data being validated.
Capability inventory: The agent utilizes Bash, Read, and Write tools across the pipeline (SKILL.md).
Sanitization: No sanitization or validation of the ingested content is performed before the agent processes it.

ship-skill