aeon-hacker-news-digest
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-generated content from Hacker News comments.\n
- Ingestion points: Fetches story and comment subtrees via the Algolia and Firebase APIs.\n
- Boundary markers: The instructions include an explicit directive to treat comment content as untrusted and ignore instructions within them.\n
- Capability inventory: The skill clusters and summarizes text; no dangerous shell or file capabilities are exposed to this data.\n
- Sanitization: Lacks programmatic sanitization, relying on model-side constraints.\n- [EXTERNAL_DOWNLOADS]: The skill fetches content from external sources.\n
- Details: Retrieves Hacker News data from the Algolia and Firebase public APIs. It also references its source code on GitHub. These references are to well-known services or the vendor's own infrastructure.
Audit Metadata