Research every provider behind Pipecat's services for new models and API affordances, writing per-service reports and local branches for clear-cut updates; publishing is scripts/provider-watch/publish.py's job, run outside this skill
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads comments on the provider-watch-reports digest issues (anyone who can comment on those issues can write text the researchers ingest without selecting a specific item), and it also reads PR titles and state from pipecat-ai/pipecat during dedupe, so GitHub issue/PR text is consumed as a standing feed.
pipecat-ai/pipecat
9a3096c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.