The Agent Skills Directory

[SAFE]: No security issues were detected. The skill follows best practices for secret management by utilizing environment variables for API keys and directs users to official vendor resources for configuration.
[EXTERNAL_DOWNLOADS]: The skill references and provides instructions for interacting with official Apideck and GitLab domains (apideck.com, gitlab.com) to fetch API specifications and documentation.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it facilitates reading data from and writing data to external issue trackers.
Ingestion points: External data is ingested through the apideck.issueTracking.tickets.list method as described in the TypeScript example.
Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted external data from the agent's instructions.
Capability inventory: The skill provides capabilities to list tickets, create tickets, and post comments on issues.
Sanitization: No data sanitization or validation logic is specified in the skill's instructions for handling the external content.

gitlab-server