The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install its core binary from external sources. Specifically, it uses npx to install @mvanhorn/printing-press from NPM and go install to fetch ticketmaster-pp-cli from the github.com/mvanhorn/printing-press-library repository. These are identified as vendor-owned resources.
[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag. This feature allows the output of any command to be transmitted to an arbitrary, user-defined URL via an HTTP POST request, which can be used to exfiltrate data processed by the skill.
[DATA_EXFILTRATION]: The skill documents a feedback mechanism that can be configured to automatically transmit local data from ~/.ticketmaster-pp-cli/feedback.jsonl to a remote endpoint if the TICKETMASTER_FEEDBACK_ENDPOINT and TICKETMASTER_FEEDBACK_AUTO_SEND environment variables are set.
[PROMPT_INJECTION]: The skill ingests untrusted data from the Ticketmaster Discovery API, creating a surface for indirect prompt injection. Malicious instructions embedded in event titles or descriptions could potentially influence the agent's behavior.
Ingestion points: Data is retrieved from the Ticketmaster Discovery API via the ticketmaster-pp-cli commands.
Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions within the retrieved API data.
Capability inventory: The skill has access to the file system (via Read Bash and the --deliver file:<path> flag) and the network (via the --deliver webhook:<url> flag).
Sanitization: There is no evidence of sanitization or filtering of the external API content before it is processed by the agent.

pp-ticketmaster