The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to fetch and process work item data from GitLab via the glab work-items list command. This creates an attack surface where malicious instructions embedded in GitLab content could influence the agent's actions. * Ingestion points: Data enters the agent's context through the output of glab work-items list as documented in SKILL.md and the command reference. * Boundary markers: The skill does not provide instructions for the agent to use delimiters or to treat the retrieved content as untrusted. * Capability inventory: The agent can execute glab commands to create, update, and delete work items, and can read local files via the --description-file and --attach flags. * Sanitization: No sanitization or filtering of retrieved GitLab content is specified.

glab-workitems