The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the openspec CLI and the mv utility to archive project changes based on user input.
[PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection because it interpolates untrusted user data into shell commands without sanitization.
Ingestion points: The <name> argument supplied by the user during the /opsx:archive command invocation.
Boundary markers: Absent. The instructions do not provide delimiters or warnings to treat the user input as untrusted data.
Capability inventory: Execution of openspec status and filesystem mv commands as described in SKILL.md.
Sanitization: Absent. There are no instructions to validate, escape, or filter the user-supplied string before it is used in a shell context.

opsx-archive