The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches a CLI utility from the npm registry and GitHub repositories associated with the author's toolset (@mvanhorn/printing-press and mvanhorn/printing-press-library).
[COMMAND_EXECUTION]: Employs shell commands via the jira-pp-cli tool to perform Jira operations such as retrieving issues, managing project categories, and updating banners.
[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> parameter which enables sending command results to an external endpoint, creating a potential path for data exfiltration.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates data from Jira without protective boundary markers or sanitization.
Ingestion points: Data is retrieved from external Jira sources through commands like issue get, comment, and attachment get-content.
Boundary markers: Absent; there are no instructions to delimit untrusted content.
Capability inventory: Uses the Read Bash tool to execute CLI logic.
Sanitization: Absent; the skill does not specify validation or filtering for data fetched from the Jira API.

pp-jira