The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the linkding command-line utility. It includes safety recommendations, such as quoting URLs and search text to mitigate potential command injection via shell metacharacters.
[EXTERNAL_DOWNLOADS]: The skill relies on an external binary provided by the chickenzord/linkding-cli repository on GitHub. While it doesn't automate the download, it directs the agent/user to this specific third-party resource.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by ingesting and processing data from a Linkding instance, which may contain attacker-controlled content in bookmark titles or descriptions.
Ingestion points: The skill reads structured data via linkding bookmark list and linkding bookmark get (documented in SKILL.md).
Boundary markers: The instructions lack explicit delimiters or instructions to the agent to ignore potentially malicious commands embedded within the retrieved bookmark data.
Capability inventory: The skill has the capability to execute shell commands (linkding) and perform network operations via that binary.
Sanitization: No sanitization or validation of the retrieved bookmark fields is specified before the data is presented to the agent's context.

linkding-cli