Hacker News Digest
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches story metadata and discussion threads from Hacker News's public APIs on Firebase and Algolia.\n- [COMMAND_EXECUTION]: Executes shell commands including
curlandjqfor data processing, and invokes a local notification script./notify.\n- [PROMPT_INJECTION]: The skill processes untrusted content from external sources, making it susceptible to indirect prompt injection.\n - Ingestion points: Retrieves news summaries and comments from
hacker-news.firebaseio.com,hn.algolia.com, and external article URLs via WebFetch fallback.\n - Boundary markers: No explicit delimiters or boundary markers are utilized to separate external data from agent instructions.\n
- Capability inventory: Includes shell command execution (
curl,jq,date), local file system access (read/write inmemory/and.cache/), and local script execution (./notify).\n - Sanitization: Content is filtered by length and basic keyword exclusion, but no security-focused sanitization or instruction filtering is applied to the retrieved content.
Audit Metadata