The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes several command-line tools to manage the issue lifecycle.
It executes git commands to add and commit issue files to the local repository.
It utilizes platform-specific CLI tools including gh (GitHub), glab (GitLab), and tea (Gitea) to create remote issues based on the repository's configuration.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and stores untrusted data provided by the user.
Ingestion points: The skill accepts descriptions and evidence (gap/nợ + bằng chứng) which are written directly into markdown files within the llmwiki/wiki/sources/draft/ directory.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the ingested data as untrusted or to ignore potential instructions embedded within the text.
Capability inventory: The skill possesses capabilities to read/write files, perform Git commits, and interact with remote network services via CLI tools.
Sanitization: The workflow does not specify any sanitization, escaping, or validation steps for the input data before it is persisted in the ledger or uploaded to remote trackers.

raise-issue