The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local CLI commands for the openspec tool, including openspec list, openspec status, and openspec instructions apply. These operations are consistent with the skill's stated purpose of managing and verifying change artifacts provided by the vendor.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes content from untrusted external sources during the verification process. 1. Ingestion points: The skill reads documentation files (tasks.md, specs/*.md, design.md) and project source code retrieved via directory context. 2. Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent treats the content of these files as data only, potentially allowing embedded text to influence the agent's logic. 3. Capability inventory: The agent is permitted to read local files and execute specific vendor CLI tools; it does not possess network egress or general file writing capabilities. 4. Sanitization: The instructions do not provide methods for sanitizing or validating the ingested content before it is parsed for requirement extraction and implementation mapping.

openspec-verify-change