The Agent Skills Directory

[COMMAND_EXECUTION]: The skill identifies and executes shell commands for running integration tests. Evidence: In SKILL.md, the workflow involves resolving an 'ordered task-scoped runner set' and executing the 'exact detected command' found in repository evidence.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository files to determine its execution behavior, creating a surface for injection. 1. Ingestion points: The skill reads AGENTS.md, CONTEXT.md, task files, and project specifications (SKILL.md). 2. Boundary markers: Absent; there are no explicit instructions to use delimiters or ignore instructions embedded within the ingested repository files. 3. Capability inventory: The skill has the capability to execute shell commands and modify test files based on the ingested data (SKILL.md). 4. Sanitization: Absent; no validation or sanitization process is described for the commands resolved from external documentation before they are executed.

integration-test