The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the openspec and codegraph CLI tools to retrieve status and explore code dependencies. Evidence: The skill defines steps involving openspec status --change "<name>" --json and codegraph explore "<capability terms>" in SKILL.md.
[PROMPT_INJECTION]: The skill processes 'delta specs' and applies them to 'main specs', creating a vulnerability surface for indirect prompt injection where malicious instructions could be embedded in the specification files. Ingestion points: Reads delta specs from paths defined in artifactPaths.specs.existingOutputPaths in SKILL.md. Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions found within the spec files. Capability inventory: The agent is granted capabilities to read and edit local files (main specs) and execute CLI commands. Sanitization: Absent; the skill does not describe any validation or filtering of the content retrieved from delta specs before interpolation into the workflow.

opsx-sync