sponsored-newsletter-finder

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from web search results in Phases 1, 2, and 3 and incorporates it into a markdown report. * Ingestion points: Web search results (SKILL.md). * Boundary markers: Absent. * Capability inventory: File-write to current working directory (SKILL.md). * Sanitization: Absent.
  • [NO_CODE]: This skill consists of instructions and metadata without any accompanying executable scripts or binary files, relying on the agent to interpret the workflow using standard tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 10:48 AM