The Agent Skills Directory

[DATA_EXFILTRATION]: The skill documentation describes a --deliver webhook:<url> flag for every command. This feature allows the agent to POST command results, which may contain sensitive Jira issue data, project configurations, or user details, to an arbitrary external URL.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process unstructured data from Jira, creating a significant surface for indirect prompt injection.
Ingestion points: Tools such as issue get, comment, changelog, and attachment get-content (found in SKILL.md) retrieve user-generated content from Jira.
Boundary markers: The skill instructions do not specify any boundary markers or instructions for the agent to ignore embedded commands within the retrieved data.
Capability inventory: The skill has the capability to write to the local file system (--deliver file:<path>), exfiltrate via network (--deliver webhook:<url>), and perform administrative actions within the Jira instance.
Sanitization: There is no evidence of sanitization or filtering applied to external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the jira-pp-cli binary. It provides instructions to download this from the vendor's official sources using npx -y @mvanhorn/printing-press-library or go install github.com/mvanhorn/printing-press-library/.... While these are external dependencies, they are provided by the skill's author (mvanhorn).

pp-jira