hn-search
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from the public Hacker News forum via the Algolia API. While this presents a theoretical surface for indirect prompt injection, the risk is inherent to the skill's primary purpose of performing external searches and is mitigated by the agent's display-only processing of the fetched data.
- Ingestion points: External data is retrieved from the Algolia API (hn.algolia.com) as described in SKILL.md.
- Boundary markers: None explicitly defined for the search results, though content is suggested to be presented in a structured list format.
- Capability inventory: The skill uses web_fetch for data retrieval and suggests the use of a system command (date +%s) to calculate Unix timestamps for filtering.
- Sanitization: The skill instructions do not specify a sanitization step for the HTML story_text or comment_text returned by the API before they are presented to the user.
Audit Metadata