The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute local scripts scripts/media_registry.py and scripts/media_lifecycle.py to handle asset state changes and file cleanup operations.
[COMMAND_EXECUTION]: The workflow involves triggering a project-impact tool when asset replacements affect downstream project continuity.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project-relative paths and source artifacts, creating a potential vector for indirect prompt injection.
Ingestion points: The agent is instructed to read ../../references/MEDIA_REGISTRY.md, project dependencies, and source artifacts.
Boundary markers: No delimiters or instructions to ignore embedded commands in the ingested data are present.
Capability inventory: The skill has the capability to run local scripts, modify .jsonl files, and perform file deletions via the lifecycle script.
Sanitization: The instructions do not specify any validation, escaping, or sanitization steps for the data retrieved from external files.

asset-approval