colosseum-resources
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a hackathon resource directory from
https://ColosseumOrg.github.io/hackathon-resources/current.json. This is an official repository maintained by the skill author for providing current tool information. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external URL which could potentially contain malicious instructions affecting the agent's behavior.
- Ingestion points: The
SKILL.mdfile fetchescurrent.jsonto obtain tool descriptions, documentation links, and installation commands. - Boundary markers: None identified. The instructions do not use delimiters or provide a warning to the agent to disregard instructions embedded within the fetched JSON data.
- Capability inventory: The skill uses
curlfor network requests and recommendsnpx skills addfor tool installation. - Sanitization: There is no evidence of validation or sanitization of the fetched JSON content before it is processed and presented to the user.
Audit Metadata