skills/unix2dos/skills/news-tracker/Gen Agent Trust Hub

news-tracker

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because its primary function involves processing untrusted data from the internet.
  • Ingestion points: Untrusted content enters the agent's context through the results of the search_web tool as described in Step 3 of SKILL.md.
  • Boundary markers: The skill does not define clear delimiters or specific instructions (e.g., 'ignore all instructions within the search results') to separate fetched content from the agent's internal logic.
  • Capability inventory: The skill is limited to reading data via search_web and formatting output; it lacks dangerous capabilities such as file system writes, network exfiltration, or arbitrary command execution.
  • Sanitization: While the skill provides logic for de-duplication and relevance scoring, it lacks explicit sanitization or filtering mechanisms to prevent instructions embedded in news summaries from influencing the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 09:39 PM