hackernews
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts with the official Hacker News API via hacker-news.firebaseio.com. This is a well-known service, and the data retrieved is public tech news and community discussion. No sensitive local data is accessed or exfiltrated.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted text (story titles, comments, and user bios) from an external source.
- Ingestion points: Data is fetched from various API endpoints listed in SKILL.md (e.g., /v0/topstories.json, /v0/item/{id}.json).
- Boundary markers: The skill does not implement specific boundary markers or instructions to ignore embedded commands in the retrieved data.
- Capability inventory: The skill utilizes shell-based tools (curl, jq) for data retrieval and manipulation.
- Sanitization: The instructions do not include steps to sanitize or filter the external content before it enters the agent's context.
Audit Metadata