The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external websites and YouTube to generate blog posts.
Ingestion points: News content is fetched from various domains including insidegnss.com, gpsworld.com, and company newsrooms such as trimble.com and hexagon.com as defined in SKILL.md.
Boundary markers: None identified. The workflow does not specify the use of delimiters or instructions for the agent to ignore embedded commands within the fetched news.
Capability inventory: The skill has the ability to write files to the local filesystem (src/content/posts/) and perform git commits.
Sanitization: There is no evidence of content sanitization or validation before the external data is interpolated into the MDX template.
[EXTERNAL_DOWNLOADS]: The skill fetches information from several well-known industry sources and services.
It retrieves tech news coverage from Bloomberg via YouTube and industry-specific updates from publications like Inside GNSS and GPS World, as well as official newsrooms for positioning technology vendors.
[COMMAND_EXECUTION]: The skill includes instructions for managing a repository.
Step 5 of the workflow describes a commit process ("feat: add daily tech & GNSS news digest") which implies the execution of version control commands.

daily-news-digest