The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest content from external, user-controlled sources within Jira that could contain adversarial instructions.
Ingestion points: Commands such as acli jira workitem view, acli jira workitem search, and acli jira workitem comment list retrieve external data into the agent's context (SKILL.md).
Boundary markers: No specific boundary markers or instructions to disregard embedded commands in Jira data are provided in the skill documentation.
Capability inventory: The skill includes high-impact capabilities such as workitem delete, project delete, transition, and edit, which could be exploited if an injection attack is successful (SKILL.md).
Sanitization: The instructions do not mention sanitizing or filtering retrieved content before the agent processes or acts upon it.
[COMMAND_EXECUTION]: The skill relies on shell command execution for its primary functions, including management of work items and projects.
Evidence: The skill provides numerous examples of using the acli CLI tool and curl for interacting with Jira APIs, including bulk operations and attachment handling (SKILL.md).

acli