The Agent Skills Directory

[Unverifiable Dependencies] (MEDIUM): The skill requires the installation of the datacommons-client Python package via uv pip. While this is the official client for a known platform, the GitHub organization datacommonsorg is not included in the 'Trusted External Sources' list, making it an unverifiable dependency.
[Indirect Prompt Injection] (LOW): The skill possesses a vulnerability surface for indirect prompt injection as it ingests untrusted data from an external API.
Ingestion points: Data enters the agent context through methods like client.observation.fetch(), client.node.fetch(), and client.resolve.fetch() as documented in SKILL.md, references/observation.md, and references/node.md.
Boundary markers: Absent. There are no instructions provided to the agent to treat the statistical data or graph labels as potentially adversarial or to use delimiters.
Capability inventory: The skill is primarily a data retrieval tool. It lacks high-risk capabilities such as arbitrary command execution, file system modification, or network writing (beyond API requests), limiting the potential impact of an injection.
Sanitization: Absent. The skill examples show direct processing of external strings into the agent's context without validation or escaping.

datacommons-client