hackernews
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
bash,curl, andjqto execute API requests and process JSON responses. These commands are used for their intended purpose of data retrieval and transformation.\n- [EXTERNAL_DOWNLOADS]: Fetches data fromhacker-news.firebaseio.com, which is the well-known and official domain for the Hacker News API.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to the ingestion of untrusted external content (titles, comments, and bios).\n - Ingestion points: Untrusted data enters the agent context via
curlrequests to the Hacker News API defined inSKILL.md.\n - Boundary markers: No specific delimiters or boundary markers are implemented to wrap the external text content.\n
- Capability inventory: The skill uses shell execution capabilities (
curl,jq,bash).\n - Sanitization: No sanitization or filtering is applied to the retrieved text fields before they are processed by the agent.
Audit Metadata