The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple shell commands to validate and release software.
Evidence includes calls to go test, go vet, golangci-lint, git, and codex command-line tools.
It also executes local Python validation scripts located at ${CODEX_HOME:-$HOME/.codex}/skills/.system/.
[INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data that could contain malicious instructions.
Ingestion points: The skill is instructed to read AGENTS.md and repository diffs to confirm release versions and update documentation.
Boundary markers: Absent. There are no explicit instructions to the agent to ignore or delimit instructions found within the repository files.
Capability inventory: The skill has the capability to write to the file system, execute shell commands, and perform network operations via git push and codex plugin marketplace upgrade.
Sanitization: Absent. The skill does not define methods to filter or escape instructions embedded in the documentation it reads.

release-tractor