The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The skill documentation includes examples that perform network requests to an external API (https://openjung.org/api/questions). This domain is not on the pre-approved whitelist. The requests are consistent with the skill's stated purpose of retrieving personality assessment data.
[DATA_EXFILTRATION] (LOW): The skill transmits user-provided data (test answers) to an external server (https://openjung.org/api/calculate) via POST requests for scoring. This is the intended functionality of the skill, but users should be aware that their assessment responses are sent to a third party.
[Indirect Prompt Injection] (LOW): The skill processes external data that could potentially contain malicious instructions.
Ingestion points: Data enters the agent context through the /api/questions endpoint as shown in SKILL.md.
Boundary markers: No explicit delimiters or boundary markers are defined for the fetched content.
Capability inventory: The skill utilizes fetch for network communication.
Sanitization: No sanitization or validation of the retrieved question content is described in the integration guide.

openjung-api