hackernews
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches story lists, item details, and user profiles from the official Hacker News API at
hacker-news.firebaseio.com. - [COMMAND_EXECUTION]: Uses shell commands (
curl,jq) and bash loops to interact with API endpoints and process JSON data. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-generated content from Hacker News (such as comments, story text, and user bios) which could theoretically contain malicious instructions targeting the AI agent.
- Ingestion points: API responses from the item (
/v0/item/{id}.json) and user (/v0/user/{id}.json) endpoints as described inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content for the fetched strings.
- Capability inventory: Utilizes shell commands for network operations and data parsing via
curlandjq. - Sanitization: No explicit sanitization or validation of the fetched text is performed before the agent processes the information.
Audit Metadata