The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The diagram.html file includes a script tag that fetches the Mermaid.js library from https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.min.js. This is a well-known and trusted content delivery network used for rendering the workflow diagrams.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the aggregation of external data.
Ingestion points: The skill collects build results, test failure details, and container logs from worker skills (ln-781, ln-782, ln-783) as described in Phases 2, 3, and 4 of SKILL.md.
Boundary markers: There are no explicit delimiters or boundary instructions defined to prevent the agent from being influenced by potentially malicious content embedded in the logs or reports it processes.
Capability inventory: The skill has the capability to delegate tasks to other worker skills and generate a final report for the user, but it does not directly execute system commands or perform network exfiltration itself.
Sanitization: There is no evidence of sanitization or validation of the text returned by worker skills before it is included in the final report and displayed to the user.

ln-780-bootstrap-verifier